CN117272145A - Health state evaluation method and device of switch machine and electronic equipment - Google Patents
Health state evaluation method and device of switch machine and electronic equipment Download PDFInfo
- Publication number
- CN117272145A CN117272145A CN202311278441.3A CN202311278441A CN117272145A CN 117272145 A CN117272145 A CN 117272145A CN 202311278441 A CN202311278441 A CN 202311278441A CN 117272145 A CN117272145 A CN 117272145A
- Authority
- CN
- China
- Prior art keywords
- health state
- membership
- matrix
- determining
- health
- 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
- 230000036541 health Effects 0.000 title claims abstract description 171
- 238000011156 evaluation Methods 0.000 title claims abstract description 62
- 239000011159 matrix material Substances 0.000 claims abstract description 151
- 238000010606 normalization Methods 0.000 claims abstract description 41
- 238000007405 data analysis Methods 0.000 claims abstract description 34
- 238000004458 analytical method Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 13
- 239000013598 vector Substances 0.000 claims description 67
- 238000000034 method Methods 0.000 claims description 37
- 230000003862 health status Effects 0.000 claims description 34
- 230000006870 function Effects 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000013139 quantization Methods 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims 1
- 238000012854 evaluation process Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 5
- 201000010099 disease Diseases 0.000 description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000011002 quantification Methods 0.000 description 4
- 230000008439 repair process Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000005713 exacerbation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- 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
Abstract
The invention provides a health state evaluation method and device of a switch machine and electronic equipment, relating to the technical field of health management of railway signal equipment, and comprising the following steps: acquiring health state grading information and detecting indexes corresponding to various influence factors influencing the health state of the switch machine; carrying out data analysis processing on the detection indexes, and respectively determining normalization probability and normalization severity corresponding to each influence factor; determining a membership matrix of each influence factor on each health state grading information based on the normalization probability, the normalization severity and the health state grading information through a preset membership analysis function; determining a weight matrix corresponding to each influence factor based on the membership matrix and the health state grading information through a preset data analysis model; and determining a target health state evaluation result of the switch machine according to the membership matrix and the weight matrix. The invention can remarkably improve the evaluation accuracy and simplify the evaluation process, thereby reducing the evaluation cost.
Description
Technical Field
The invention relates to the technical field of health management of railway signal equipment, in particular to a health state assessment method and device of a switch machine and electronic equipment.
Background
The switch machine is important signal equipment of switch conversion equipment, and is easily influenced by various factors indoors and outdoors because of the complex structure of the switch machine, so that the health state of the switch machine is not only related to the state of the switch machine, but also influenced by various uncertain factors such as indoors and outdoors. At present, related technologies propose that an equipment health mathematical model can be established based on experiments and mechanism researches, or a fuzzy evaluation matrix is established through fuzzy evaluation, so that an evaluation result is comprehensively obtained, but the scheme has higher evaluation cost and lower evaluation accuracy.
Disclosure of Invention
Therefore, the present invention aims to provide a method, a device and an electronic device for evaluating the health status of a switch machine, which can significantly improve the evaluation accuracy, simplify the evaluation process and reduce the evaluation cost.
In a first aspect, an embodiment of the present invention provides a method for evaluating a health status of a switch machine, including: acquiring health state grading information and detecting indexes corresponding to various influence factors influencing the health state of the switch machine; carrying out data analysis processing on the detection indexes, and respectively determining normalization probability and normalization severity corresponding to each influence factor; determining a membership matrix of each influence factor on each health state grading information based on the normalization probability, the normalization severity and the health state grading information through a preset membership analysis function; determining a weight matrix corresponding to each influence factor based on the membership matrix and the health state grading information through a preset data analysis model; and determining a target health state evaluation result of the switch machine according to the membership matrix and the weight matrix.
In one embodiment, the step of determining a membership matrix of each influence factor to each health state classification information based on the normalized probability, the normalized severity and the health state classification information by presetting a membership analysis function includes: carrying out numerical quantization processing on the normalized probability and normalized severity of each influence factor through a preset membership function, and determining a membership vector set; wherein the membership vector set includes: normalized probability and normalized severity of each influence factor are respectively membership degree vectors when the influence factors are affiliated to different health state grading information; and establishing a membership matrix according to the membership vector set.
In one embodiment, a method comprises: aiming at different health state grading information, invoking corresponding numerical matching rules from preset membership functions, and calculating to obtain quantized numerical values; and carrying out numerical quantification processing on the normalized probability and normalized severity of each influence factor by using a numerical matching rule, and determining a membership vector of the influence factor when the influence factor belongs to the health state grading information.
In one embodiment, the step of determining a weight matrix corresponding to each influence factor based on the membership matrix and the health status classification information by a preset data analysis model includes: carrying out association coefficient calculation on the membership matrix and the health state grading information through a preset data analysis model, and determining an association coefficient matrix corresponding to each health state grading information; and determining a weight matrix corresponding to each influence factor according to the association coefficient matrix.
In one embodiment, the step of calculating the association coefficient of the membership matrix and the health status classification information by a preset data analysis model to determine the association coefficient matrix corresponding to each health status classification information includes: acquiring a mother sequence vector corresponding to each piece of health state grading information, wherein the mother sequence vector is used for determining a standard coordinate vector of each piece of health state grading information; performing distance analysis on the mother sequence vector corresponding to each health state grading information and the membership matrix of each influence factor, and determining a minimum distance global variable and a maximum distance global variable; and determining an association coefficient matrix corresponding to the health state grading information based on the minimum distance global variable and the maximum distance global variable through a preset data analysis model.
In one embodiment, the step of determining a weight matrix corresponding to each influencing factor according to the association coefficient matrix includes: matching the association coefficient matrix with the membership matrix to determine the association degree between each influence factor and the parent sequence vector of the health state grading information when the influence factors are respectively in different health state grading information; determining a weight vector of each influence factor according to the average value of the association degree of any influence factor in the grading information of different health states; and integrating the weight vectors of all the influence factors to determine a weight matrix.
In one embodiment, the step of determining the target health assessment result of the switch machine according to the membership matrix and the weight matrix includes: determining a health evaluation matrix according to the membership matrix and the weight matrix, wherein the health evaluation matrix comprises: evaluation values corresponding to the health status classification information; and determining the health state grading information corresponding to the maximum evaluation value as a target health state evaluation result.
In a second aspect, an embodiment of the present invention further provides a health status assessment device of a switch machine, where the device includes: the data acquisition module acquires health state grading information and detection indexes corresponding to various influence factors influencing the health state of the switch machine; the data analysis module is used for carrying out data analysis processing on the detection indexes and respectively determining normalization probability and normalization severity corresponding to each influence factor; the membership analysis module is used for determining a membership matrix of each influence factor on each health state grading information based on the normalization probability, the normalization severity and the health state grading information by presetting a membership analysis function; the weight analysis module is used for determining a weight matrix corresponding to each influence factor based on the membership matrix and the health state grading information through a preset data analysis model; and the health state evaluation module is used for determining a target health state evaluation result of the switch machine according to the membership matrix and the weight matrix.
In a third aspect, embodiments of the present invention also provide an electronic device comprising a processor and a memory storing computer executable instructions executable by the processor, the processor executing the computer executable instructions to implement the method of any one of the first aspects.
In a fourth aspect, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions that, when invoked and executed by a processor, cause the processor to implement the method of any one of the first aspects.
The embodiment of the invention has the following beneficial effects:
according to the health state assessment method, the health state assessment device and the electronic equipment of the switch machine, after health state classification information and detection indexes corresponding to all influence factors influencing the health state of the switch machine are obtained, data analysis processing is carried out on the detection indexes, normalization probability and normalization severity corresponding to all influence factors are respectively determined, the membership degree matrix of each influence factor for each health state classification information is determined based on the normalization probability, the normalization severity and the health state classification information through a preset membership degree analysis function, the weight matrix corresponding to each influence factor is determined based on the membership degree matrix and the health state classification information through a preset data analysis model, and finally, the target health state assessment result of the switch machine is determined according to the membership degree matrix and the weight matrix.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for evaluating the health status of a switch machine according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for evaluating the health status of a switch machine according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a health state assessment device of a switch machine according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described in conjunction with the embodiments, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The switch machine is important signal equipment of switch conversion equipment, and because the switch machine is complex in structure and is easily influenced by various factors indoors and outdoors, the health state of the switch machine is not only related to the state of the switch machine, but also influenced by various uncertain factors such as indoors and outdoors, and at present, the health evaluation in the PHM field has the following two main schemes: 1. based on experiments and mechanism researches, establishing a device health mathematical model; 2. fuzzy evaluation is carried out, a fuzzy evaluation matrix is established, and evaluation results are comprehensively obtained, but the two schemes need a more complex theoretical research basis and a large amount of scientific experiment basis, and the conditions are not mature as actual landing technology. Based on the above, the health state evaluation method of the switch machine provided by the embodiment of the invention can remarkably improve the evaluation accuracy, simplify the evaluation process and reduce the evaluation cost.
Referring to fig. 1, a flow chart of a method for evaluating the health status of a switch machine mainly includes the following steps S102 to S110:
step S102, acquiring health state grading information and detecting indexes corresponding to various influencing factors influencing the health state of the switch machine. Among other factors affecting the health of the switch machine may include: the first-level alarming frequency generated in the last 1 month of the switch, the second-level alarming frequency generated in the last 1 month of the switch, the major repair frequency in the last half year of the switch, the middle repair frequency in the last half year of the switch, the minor repair frequency in the last half year of the switch, the use time of the switch on the way, the pulling frequency in the last 1 month of the switch, and the temperature and humidity exceeding alarming frequency in the last 1 month of the switch. The health status ranking information may include: health, well being, attention, exacerbation and disease. In one embodiment, the health status classification information and the number, division and specific project of the influencing factors can be determined by intelligently analyzing historical operation and detection indexes of the switch machine.
Step S104, performing data analysis processing on the detection index, and determining a normalization probability and a normalization severity corresponding to each influence factor, respectively, where in one embodiment, the normalization probability is a probability that a certain influence factor becomes a fact, for example: the system uses statistics of the number of alarms of the factor in each month of each device in history to obtain a histogram distribution of the factor, and uses the histogram distribution to obtain a probability value corresponding to the number of alarms of the factor in each month of the device, in another embodiment, the normalized severity represents the damage degree caused by the health state of the device after the influence factor occurs, and the damage degree is represented by a numerical value between (0 and 1), wherein 1 represents severity, and 0 represents no influence at all. For example: the device only generates 1 slight pre-alarm in a certain month, and the alarm severity is defined as 0; whereas a device fails up to 50 times a month (in the prior art, the average failure of the device is typically several times a month), when the health status of the device should be a disease, the severity corresponding to the influencing element should be defined as 1.
Step S106, determining a membership matrix of each influence factor on each health state grading information based on the normalized probability, the normalized severity and the health state grading information by presetting a membership analysis function, wherein the number of columns of the membership matrix is equal to the number of categories of the health state grading information, the number of rows is equal to the product of the number of influence factors and the estimated dimension number, and when the estimated dimension is the occurrence probability and the severity, the estimated dimension number is 2, and in one embodiment, calculating the membership matrix by using the normalized probability value and the normalized severity value of each influence factor of the quantified membership function on the health state of the equipment.
Step S108, determining a weight matrix corresponding to each influence factor based on the membership matrix and the health state grading information through a preset data analysis model, wherein the weight matrix comprises the association degree of each influence factor in different health state grading information, the number of lines of the weight matrix of each influence factor is 1, and the number of columns is the product of the number of influence factors and the number of evaluation dimensions.
Step S110, determining the target health state evaluation result of the switch machine according to the membership matrix and the weight matrix.
The method for evaluating the health state of the switch machine, provided by the embodiment of the invention, can remarkably improve the evaluation accuracy, simplify the evaluation process and reduce the evaluation cost.
The embodiment of the invention also provides an implementation manner for evaluating the health state of the switch machine, referring to a specific flow diagram of a health state evaluation method of the switch machine shown in fig. 2, specifically comprising the following (1) to (3):
(1) Carrying out histogram statistics by utilizing historical data of health influence factors of the first 6 months, generating a histogram distribution table of each influence, calculating occurrence probability under the corresponding numerical conditions of various factors according to the statistical histogram (for example, the histogram distribution of the pulling times of the switch machine in the last 6 months can be obtained by carrying out statistics on the pulling times of the switch machine in each month, thereby calculating the frequency interval probability corresponding to the pulling times of the switch machine in the last 1 month), namely, according to the generated histogram distribution and the data of each influence factor in the current month, acquiring the normalization probability and the normalization severity corresponding to each influence factor, calculating a membership matrix of the normalization probability and the normalization severity of each influence factor on the health grade of the switch machine in 5 classes, wherein when the health state grading information is 5 classes, the number of influence factors is 8, the membership matrix M is a matrix of 16 rows and 5 columns, carrying out numerical quantization processing on the normalization probability and the normalization severity of each influence factor in 1 month, determining a membership vector set according to the generated histogram distribution and the data of each influence factor in the current month, and establishing a membership vector set, wherein the membership vector set comprises the membership vector set: the normalization probability and the normalization severity of each influence factor are membership vectors when the influence factors are affiliated to different health state grading information respectively, in one implementation mode, corresponding numerical matching rules can be called from a preset membership analysis function aiming at different health state grading information, the normalization probability and the normalization severity of each influence factor are subjected to numerical quantification processing by using the numerical matching rules, and the membership vectors of the influence factors when the influence factors are affiliated to the health state grading information are determined, wherein the specific numerical matching rules are as follows:
in practical application, the normalized probability p of each influence factor is calculated on the membership degree of the 'health' state level: when p=0, the membership is 1; when 0 < p < 0.4, the membership degree is (0.4-p)/0.4; when p is more than or equal to 0.4 and less than or equal to 1, the membership degree is 0;
the normalized probability p of each influence factor is calculated by the membership degree of the 'good' state grade: when p is more than or equal to 0 and less than 0.2, the membership degree is 0; when p is more than or equal to 0.2 and less than 0.4, the membership degree is (p-0.2)/0.2; when p is more than or equal to 0.4 and less than 0.6, the membership degree is (0.6-p)/0.2; when p is more than or equal to 0.6 and less than or equal to 1, the membership degree is 0;
the normalized probability p of each influence factor is subject to the membership calculation of the 'attention' state level: when p is more than or equal to 0 and less than 0.4, the membership degree is 0; when p is more than or equal to 0.4 and less than 0.6, the membership degree is (p-0.4)/0.2; when p is more than or equal to 0.6 and less than 0.8, the membership degree is (0.8-p)/0.2; when p is more than or equal to 0.8 and less than or equal to 1, the membership degree is 0;
the normalized probability p of each influence factor is subject to the membership calculation of the "worsening" state level: when p is more than or equal to 0 and less than 0.6, the membership degree is 0; when p is more than or equal to 0.6 and less than 0.8, the membership degree is (p-0.6)/0.2; when p is more than or equal to 0.8 and less than 1, the membership degree is (1-p)/0.2; when p=1, the membership is 0;
the normalized probability p of each influencing factor is calculated by the membership degree of the 'disease' state grade: when p is more than or equal to 0 and less than 0.6, the membership degree is 0; when p is more than or equal to 0.6 and less than 1, the membership degree is (p-0.6)/0.4; when p=1, the membership is 1.
In practical application, each influence factor normalizes the degree of severity q and is subordinate to the membership calculation of "health" state grade: when q=0, the membership is 1; when 0 < q < 0.4, the membership degree is (0.4-q)/0.4; when q is more than or equal to 0.4 and less than or equal to 1, the membership degree is 0;
calculation of membership degree of each influence factor normalized severity q to "good" state grade: when q is more than or equal to 0 and less than 0.2, the membership degree is 0; when q is more than or equal to 0.2 and less than 0.4, the membership degree is (q-0.2)/0.2; when q is more than or equal to 0.4 and less than 0.6, the membership degree is (0.6-q)/0.2; when q is more than or equal to 0.6 and less than or equal to 1, the membership degree is 0;
membership calculation of each influence factor normalized severity q to "attention" state class: when q is more than or equal to 0 and less than 0.4, the membership degree is 0; when q is more than or equal to 0.4 and less than 0.6, the membership degree is (q-0.4)/0.2; when q is more than or equal to 0.6 and less than 0.8, the membership degree is (0.8-q)/0.2; when q is more than or equal to 0.8 and less than or equal to 1, the membership degree is 0;
the normalized severity of each influencing factor is subject to the membership calculation of the "worsening" state class: when q is more than or equal to 0 and less than 0.6, the membership degree is 0; when q is more than or equal to 0.6 and less than 0.8, the membership degree is (q-0.6)/0.2; when q is more than or equal to 0.8 and less than 1, the membership degree is (1-q)/0.2; when q=1, the membership is 0;
calculation of membership of each influence factor normalized severity to "disease" status class: when q is more than or equal to 0 and less than 0.6, the membership degree is 0; when q is more than or equal to 0.6 and less than 1, the membership degree is (q-0.6)/0.4; when q=1, the membership is 1.
(2) Calculating an association matrix of each influence factor on the health state of the switch machine and a weight matrix of each influence factor, wherein the weight matrix of each influence factor is a matrix of 1 row and 16 columns, in one implementation mode, carrying out association coefficient calculation on the membership matrix and the health state grading information through a preset data analysis model, determining an association coefficient matrix corresponding to each health state grading information, and determining the weight matrix corresponding to each influence factor according to the association coefficient matrix, wherein the steps comprise the following steps (a) to (b):
(a) Acquiring a parent sequence vector corresponding to each item of health state grading information, performing distance analysis on the parent sequence vector corresponding to each item of health state grading information and a membership matrix of each item of influence factors, determining a minimum distance global variable and a maximum distance global variable, and determining an association coefficient matrix corresponding to each item of health state grading information based on the minimum distance global variable and the maximum distance global variable through a preset data analysis model, wherein the parent sequence vector is used for determining a standard coordinate vector of each item of health state grading information, and in one embodiment, the health state j=1, namely a 'health' state, and the parent sequence vector is vj=v1= (1, 0); health status j=2, i.e. a "good" status, then the parent sequence vector is vj=v2= (0, 1, 0); health status j=3, i.e. the "attention" status, then the parent sequence vector is vj=v3= (0, 1, 0); health status j=4, i.e. a "worsening" status, then the parent sequence vector is vj=v4= (0, 1, 0); health status j=5, i.e. the "disease" status, the parent sequence vector is vj=v5= (0,0,0,0,1).
In one embodiment, the distances between the parent sequence vector of the 5 health status classification information of the switch machine and the membership matrix are calculated, and the global variable vj_min with the smallest distance is determined, (j=1, 2,3,4, 5), namely: v1_min, v2_min, v3_min, v4_min, v5_min; and a global variable vj_max of greatest distance, (j=1, 2,3,4, 5), namely: v1_max, v2_max, v3_max, v4_max, v5_max; transmitting the minimum distance global variable and the maximum distance global variable to a preset data analysis model, and determining an association coefficient matrix corresponding to health state grading information, wherein the method for calculating the association coefficient matrix of the equipment health grade j is as follows:
where Mi represents the ith row vector of the membership matrix and Vj is the parent sequence vector of the health class j.
In practical application, using the above-described correlation coefficient matrix calculation method, for a correlation coefficient vector between j=1 (i.e., the "healthy" rank parent sequence vector [1,0 ]) and i=1 (i.e., the first row of the membership matrix) is:
wherein, the above-mentioned association coefficient vector is a vector of five elements, namely:
R1(M1)＝[z 1,1 z 1,2 z 1,3 z 1,4 z 1,5 ]
wherein Z is a scalar.
(b) Matching the association coefficient matrix with the membership matrix to determine the association degree between each influence factor and the parent sequence vector of the health state grading information when the influence factors are respectively in different health state grading information; determining a weight vector of each influence factor according to the average value of the association degree of any influence factor in the grading information of different health states; the weight vectors of the influence factors are integrated to determine a weight matrix, and in one embodiment, the health state j=1, that is, the association degree of the influence factors under the "health" parent sequence vector is:
r 1,1 ＝mean(R 1 (M 1 ))
r 2,1 ＝mean(R 1 (M 2 ))
r 3,1 ＝mean(R 1 (M 3 ))
……
r 15,1 ＝mean(R 1 (M 15 ))
r 16,1 ＝mean(R 1 (M 16 ))
health status j=2, i.e., the degree of association of each influencing factor under the "good" parent sequence vector is:
r 1,2 ,r 2,2 ,r 3,2 ,……,r 15,2 ,r 16,2
calculating the association degree of each influence factor under the mother sequence vector of each health state grading information by sub-class pushing, and further determining the weight vector of each influence factor:
W i ＝mean(r i,1 ,r i,2 ,r i,3 ,r i,4 ,r i,5 )；i∈[1,16]
and integrating the weight vectors of all the influence factors to determine a final weight matrix.
(3) According to the weight matrix and the membership matrix, determining the health state evaluation result of the switch machine, in one implementation, firstly multiplying the weight matrix by the membership matrix according to the membership matrix and the weight matrix to determine the health state evaluation matrix of the switch machine, then determining the maximum evaluation value in the health evaluation matrix, and determining the health state grading information corresponding to the maximum evaluation value as the target health state evaluation result, wherein the health evaluation matrix comprises: and the evaluation value corresponding to each health state grading information.
In summary, the method can utilize indexes such as the last month and one-level alarm times, the box temperature and humidity alarm times, the pulling times, the last half-year major and minor repair times, the equipment on-line use time and the like of the switch machine as the influence factors of the switch machine health state assessment, input the influence factors of the whole coverage health state assessment, carry out numerical quantification on the influence factors of the last month based on the historical data of each influence factor (namely, a method for quantifying the normalization probability value P and the normalization severity value Q of each influence factor through the historical data statistics), calculate the membership matrix of each influence factor based on the probability value and the severity value by utilizing the membership function, calculate the associated coefficient matrix between the influence factors and the health grade based on the membership matrix of each influence factor, thereby calculate the weight vector of each influence factor, and finally carry out the health state assessment on the switch machine equipment by utilizing the membership matrix of each influence factor and the weight of each influence factor. Based on the state of health evaluation method of the switch machine, the evaluation accuracy can be remarkably improved, and the evaluation process is simplified, so that the evaluation cost is reduced.
For the health status assessment method provided in the foregoing embodiment, the embodiment of the present invention provides a health status assessment device, referring to a schematic structural diagram of a health status assessment device of a switch machine shown in fig. 3, the device includes the following parts:
the data acquisition module 302 acquires health state grading information and detection indexes corresponding to various influence factors influencing the health state of the switch machine;
the data analysis module 304 is used for carrying out data analysis processing on the detection indexes and respectively determining the normalization probability and the normalization severity corresponding to each influence factor;
the membership analysis module 306 determines a membership matrix of each influence factor on each health state grading information based on the normalization probability, the normalization severity and the health state grading information by presetting a membership analysis function;
the weight analysis module 308 determines a weight matrix corresponding to each influence factor based on the membership matrix and the health state grading information through a preset data analysis model;
the health status assessment module 310 determines a target health status assessment result of the switch machine according to the membership matrix and the weight matrix.
According to the health state evaluation device for the switch machine, which is provided by the embodiment of the application, the evaluation accuracy can be remarkably improved, the evaluation process is simplified, and the evaluation cost is reduced.
In one embodiment, when performing the step of determining the membership matrix of each influencing factor to each health status classification information based on the normalized probability, the normalized severity and the health status classification information by presetting the membership analysis function, the membership analysis module 306 is further configured to: carrying out numerical quantization processing on the normalized probability and normalized severity of each influence factor through a preset membership analysis function, and determining a membership vector set; wherein the membership vector set includes: normalized probability and normalized severity of each influence factor are respectively membership degree vectors when the influence factors are affiliated to different health state grading information; and establishing a membership matrix according to the membership vector set.
In one embodiment, the membership analysis module 306 is further configured to: for different health state grading information, calling a corresponding numerical matching rule from a preset membership analysis function; and carrying out numerical quantification processing on the normalized probability and normalized severity of each influence factor by using a numerical matching rule, and determining a membership vector of the influence factor when the influence factor belongs to the health state grading information.
In one embodiment, when performing the step of determining the weight matrix corresponding to each influencing factor based on the membership matrix and the health status classification information by the preset data analysis model, the weight analysis module 308 is further configured to: carrying out association coefficient calculation on the membership matrix and the health state grading information through a preset data analysis model, and determining an association coefficient matrix corresponding to each health state grading information; and determining a weight matrix corresponding to each influence factor according to the association coefficient matrix.
In one embodiment, when performing the step of calculating the association coefficient of the membership matrix and the health status classification information by the preset data analysis model and determining the association coefficient matrix corresponding to each health status classification information, the weight analysis module 308 is further configured to: acquiring a mother sequence vector corresponding to each piece of health state grading information, wherein the mother sequence vector is used for determining a standard coordinate vector of each piece of health state grading information; performing distance analysis on the mother sequence vector corresponding to each health state grading information and the membership matrix of each influence factor, and determining a minimum distance global variable and a maximum distance global variable; and determining an association coefficient matrix corresponding to the health state grading information based on the minimum distance global variable and the maximum distance global variable through a preset data analysis model.
In one embodiment, when the step of determining the weight matrix corresponding to each influencing factor according to the correlation coefficient matrix is performed, the weight analysis module 308 is further configured to: matching the association coefficient matrix with the membership matrix to determine the association degree between each influence factor and the parent sequence vector of the health state grading information when the influence factors are respectively in different health state grading information; determining a weight vector of each influence factor according to the average value of the association degree of any influence factor in the grading information of different health states; and integrating the weight vectors of all the influence factors to determine a weight matrix.
In one embodiment, when performing the step of determining the health status evaluation result of the switch machine according to the membership matrix and the weight matrix, the health status evaluation module 310 is further configured to: determining a health evaluation matrix according to the membership matrix and the weight matrix, wherein the health evaluation matrix comprises: evaluation values corresponding to the health status classification information; and determining the health state grading information corresponding to the maximum evaluation value as a target health state evaluation result.
The device provided by the embodiment of the present invention has the same implementation principle and technical effects as those of the foregoing method embodiment, and for the sake of brevity, reference may be made to the corresponding content in the foregoing method embodiment where the device embodiment is not mentioned.
The embodiment of the invention provides electronic equipment, which comprises a processor and a storage device; the storage means has stored thereon a computer program which, when executed by the processor, performs the method of any of the embodiments described above.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 100 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43, the processor 40, the communication interface 43 and the memory 41 being connected by the bus 42; the processor 40 is arranged to execute executable modules, such as computer programs, stored in the memory 41.
The memory 41 may include a high-speed random access memory (RAM, random Access Memory), and may further include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. The communication connection between the system network element and the at least one other network element is achieved via at least one communication interface 43 (which may be wired or wireless), which may use the internet, a wide area network, a local network, a metropolitan area network, etc.
Bus 42 may be an ISA bus, a PCI bus, an EISA bus, or the like. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 4, but not only one bus or type of bus.
The memory 41 is configured to store a program, and the processor 40 executes the program after receiving an execution instruction, and the method executed by the apparatus for flow defining disclosed in any of the foregoing embodiments of the present invention may be applied to the processor 40 or implemented by the processor 40.
The processor 40 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuitry in hardware or instructions in software in processor 40. The processor 40 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but may also be a digital signal processor (Digital Signal Processing, DSP for short), application specific integrated circuit (Application Specific Integrated Circuit, ASIC for short), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA for short), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory 41 and the processor 40 reads the information in the memory 41 and in combination with its hardware performs the steps of the method described above.
The computer program product of the readable storage medium provided by the embodiment of the present invention includes a computer readable storage medium storing a program code, where the program code includes instructions for executing the method described in the foregoing method embodiment, and the specific implementation may refer to the foregoing method embodiment and will not be described herein.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the above examples are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention, but it should be understood by those skilled in the art that the present invention is not limited thereto, and that the present invention is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method of evaluating the health of a switch machine, the method comprising:
acquiring health state grading information and detecting indexes corresponding to various influence factors influencing the health state of the switch machine;
performing data analysis processing on the detection indexes, and respectively determining normalization probability and normalization severity corresponding to each influence factor;
determining a membership matrix of each influence factor to each health state grading information based on the normalized probability, the normalized severity and the health state grading information through a preset membership analysis function;
determining a weight matrix corresponding to each influence factor based on the membership matrix and the health state grading information through a preset data analysis model;
and determining a target health state evaluation result of the switch machine according to the membership matrix and the weight matrix.
2. The method according to claim 1, wherein the step of determining a membership matrix of each influence factor to each health state classification information based on the normalized probability, the normalized severity, and the health state classification information by a preset membership analysis function, comprises:
carrying out numerical quantization processing on the normalized probability and the normalized severity of the influence factors of each item through a preset membership function, and determining a membership vector set; wherein the set of membership vectors comprises: the normalized probability and the normalized severity of each of the influencing factors are respectively membership degree vectors when being affiliated to different health state grading information;
and establishing the membership matrix according to the membership vector set.
3. The method of evaluating the health of a switch machine according to claim 2, characterized in that it comprises:
aiming at different health state grading information, invoking corresponding numerical matching rules from a preset membership function, and calculating to obtain a quantized numerical value;
and carrying out numerical quantization processing on the normalized probability and the normalized severity of each influence factor by utilizing the numerical matching rule, and determining a membership vector of the influence factor when the influence factor is affiliated to the health state grading information.
4. The method of claim 1, wherein the step of determining the weight matrix corresponding to each of the influence factors based on the membership matrix and the health status classification information by a preset data analysis model comprises:
performing association coefficient calculation on the membership matrix and the health state grading information through a preset data analysis model, and determining an association coefficient matrix corresponding to each health state grading information;
and determining the weight matrix corresponding to each influence factor according to the association coefficient matrix.
5. The method according to claim 4, wherein the step of calculating the association coefficients of the membership matrix and the health state classification information by a preset data analysis model to determine the association coefficient matrix corresponding to each of the health state classification information comprises:
acquiring a parent sequence vector corresponding to each item of health state grading information, wherein the parent sequence vector is used for determining a standard coordinate vector of each item of health state grading information;
performing distance analysis on the parent sequence vector corresponding to each health state grading information and the membership matrix of each influence factor, and determining a minimum distance global variable and a maximum distance global variable;
and determining the association coefficient matrix corresponding to the health state grading information based on the minimum distance global variable and the maximum distance global variable through a preset data analysis model.
6. The method of claim 4, wherein the step of determining the weight matrix corresponding to each of the influencing factors according to the correlation coefficient matrix comprises:
matching the association coefficient matrix with the membership matrix to determine the association degree between each influence factor and the parent sequence vector of the health state grading information when the health state grading information is different;
determining a weight vector of the influence factor according to the average value of the association degree of any influence factor in different health state grading information;
and carrying out integration processing on the weight vectors of the influence factors of each item, and determining the weight matrix.
7. The method of claim 1, wherein the step of determining the target health assessment result of the switch machine based on the membership matrix and the weight matrix comprises:
determining a health evaluation matrix according to the membership matrix and the weight matrix, wherein the health evaluation matrix comprises: evaluation values corresponding to the health status classification information;
and determining the health state grading information corresponding to the maximum evaluation value as a target health state evaluation result.
8. A state of health assessment device for a switch machine, the device comprising:
the data acquisition module acquires health state grading information and detection indexes corresponding to various influence factors influencing the health state of the switch machine;
the data analysis module is used for carrying out data analysis processing on the detection indexes and respectively determining the normalization probability and the normalization severity corresponding to each influence factor;
the membership analysis module is used for determining a membership matrix of each influence factor on each health state grading information based on the normalization probability, the normalization severity and the health state grading information through a preset membership analysis function;
the weight analysis module is used for determining a weight matrix corresponding to each influence factor based on the membership matrix and the health state grading information through a preset data analysis model;
and the health state evaluation module is used for determining a target health state evaluation result of the switch machine according to the membership matrix and the weight matrix.
9. An electronic device comprising a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to implement the method of any one of claims 1 to 7.
10. A computer readable storage medium storing computer executable instructions which, when invoked and executed by a processor, cause the processor to implement the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311278441.3A CN117272145A (en) | 2023-09-28 | 2023-09-28 | Health state evaluation method and device of switch machine and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311278441.3A CN117272145A (en) | 2023-09-28 | 2023-09-28 | Health state evaluation method and device of switch machine and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117272145A true CN117272145A (en) | 2023-12-22 |
Family
ID=89211981
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311278441.3A Pending CN117272145A (en) | 2023-09-28 | 2023-09-28 | Health state evaluation method and device of switch machine and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117272145A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117688278A (en) * | 2024-02-04 | 2024-03-12 | 山东麦港数据系统有限公司 | Method for calculating health index based on railway line equipment |
-
2023
- 2023-09-28 CN CN202311278441.3A patent/CN117272145A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117688278A (en) * | 2024-02-04 | 2024-03-12 | 山东麦港数据系统有限公司 | Method for calculating health index based on railway line equipment |
| CN117688278B (en) * | 2024-02-04 | 2024-04-30 | 山东麦港数据系统有限公司 | Method for calculating health index based on railway line equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20160369777A1 (en) | System and method for detecting anomaly conditions of sensor attached devices | |
| CN111783999A (en) | Data processing method and device | |
| CN107168995B (en) | Data processing method and server | |
| KR20180039205A (en) | Method and device for intelligent fault diagnosis using improved rtc(real-time contrasts) method | |
| CN111080117A (en) | Method and device for constructing equipment risk label, electronic equipment and storage medium | |
| CN117272145A (en) | Health state evaluation method and device of switch machine and electronic equipment | |
| CN113468034A (en) | Data quality evaluation method and device, storage medium and electronic equipment | |
| CN115796708B (en) | Big data intelligent quality inspection method, system and medium for engineering construction | |
| CN113591393A (en) | Fault diagnosis method, device, equipment and storage medium of intelligent substation | |
| CN114399321A (en) | Business system stability analysis method, device and equipment | |
| CN113935535A (en) | Principal component analysis method for medium-and-long-term prediction model | |
| CN113487223A (en) | Risk assessment method and risk assessment system based on information fusion | |
| CN111783883A (en) | Abnormal data detection method and device | |
| CN116740586A (en) | Hail identification method, hail identification device, electronic equipment and computer readable storage medium | |
| CN116401137A (en) | Core particle health state prediction method and device, electronic equipment and storage medium | |
| CN115293735A (en) | Unmanned factory industrial internet platform monitoring management method and system | |
| CN115293609A (en) | Method and system for constructing personnel safety responsibility and job making evaluation index weight system | |
| CN113705920A (en) | Generation method of water data sample set for thermal power plant and terminal equipment | |
| CN116956197B (en) | Deep learning-based energy facility fault prediction method and device and electronic equipment | |
| CN117035563B (en) | Product quality safety risk monitoring method, device, monitoring system and medium | |
| CN113723835B (en) | Water consumption evaluation method and terminal equipment for thermal power plant | |
| CN112580700B (en) | Data correction method, system and storage medium of electric power Internet of things meter | |
| CN117422545A (en) | Credit risk identification method, apparatus, device and storage medium | |
| CN117220915A (en) | Flow analysis method and device and electronic equipment | |
| CN117876007A (en) | Flexible resource user portrait analysis method and device based on demand response |
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 |