CN115618743B - State evaluation method and state evaluation system of sighting telescope system - Google Patents
State evaluation method and state evaluation system of sighting telescope system Download PDFInfo
- Publication number
- CN115618743B CN115618743B CN202211403115.6A CN202211403115A CN115618743B CN 115618743 B CN115618743 B CN 115618743B CN 202211403115 A CN202211403115 A CN 202211403115A CN 115618743 B CN115618743 B CN 115618743B
- Authority
- CN
- China
- Prior art keywords
- cloud
- state
- state evaluation
- weight
- evaluation index
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 144
- 238000000034 method Methods 0.000 claims abstract description 114
- 230000005484 gravity Effects 0.000 claims abstract description 51
- 238000004364 calculation method Methods 0.000 claims abstract description 19
- 238000013528 artificial neural network Methods 0.000 claims abstract description 15
- 230000008569 process Effects 0.000 claims description 26
- 239000013598 vector Substances 0.000 claims description 22
- 238000005457 optimization Methods 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 238000007621 cluster analysis Methods 0.000 claims description 10
- 230000036541 health Effects 0.000 claims description 6
- 230000003190 augmentative effect Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 230000003862 health status Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a state evaluation method and a state evaluation system of a sighting telescope system, firstly, acquiring to-be-evaluated index data of each state evaluation index of the sighting telescope system; calculating the position of the center of gravity of the cloud according to the combination weight of each index data to be evaluated and each state evaluation index; calculating membership degrees of the cloud center of gravity and the cloud models of all state levels according to the cloud center of gravity position; and determining the state grade of the sighting telescope system according to the membership degree. According to the scheme, the combined weighting method is adopted to determine the weight of each index of the system, so that the accuracy of weight calculation can be improved. By establishing an SOM neural network to cluster the system operation data, each index threshold value is determined according to the clustering result, the accuracy of the index threshold value can be improved, and the accuracy of the evaluation result is further improved.
Description
Technical Field
The present application relates to the field of state evaluation, and in particular, to a state evaluation method and a state evaluation system for a sighting telescope system.
Background
With the rapid development of the military field, the integration and informatization degree of equipment systems are continuously improved, a series of new fault problems are brought, the traditional equipment fault detection and maintenance guarantee cannot meet the requirements of the maintenance guarantee, and the fire control system is particularly obvious in this aspect. The sighting telescope system is an important component part of equipment output as one of main sources, and a special state evaluation method and an evaluation system are designed for the sighting telescope system, so that the reliability and the usability of the sighting telescope system can be improved.
The existing evaluation method is mainly determined aiming at a single signal threshold, however, the signal of the sighting telescope system is complex, and therefore, the existing method cannot accurately evaluate. In addition, the existing evaluation method mainly determines an index threshold value through expert evaluation, and has the defect of inaccurate threshold value determination result.
Disclosure of Invention
The application aims to provide a state evaluation method and a state evaluation system of a sighting telescope system, which can improve the accuracy of state evaluation of the sighting telescope system.
In order to achieve the above object, the present application provides the following solutions:
a method of state assessment of a telescope system, comprising:
acquiring index data to be evaluated of each state evaluation index of the sighting telescope system;
calculating the position of the center of gravity of the cloud according to the combination weight of each index data to be evaluated and each state evaluation index; the combination weight of each state evaluation index is determined by a combination weighting method combining an improved fuzzy analytic hierarchy process and an improved entropy weighting method; the cloud center of gravity position is the position of the cloud center of gravity in a clouding section of the state grade; the clouding interval is determined by the threshold value of each state evaluation index, and the threshold value of each state evaluation index is obtained by carrying out cluster analysis on sample index data of each state evaluation index by using a self-organizing map neural network algorithm;
calculating membership degrees of the cloud center of gravity and the cloud models of all state levels according to the cloud center of gravity position; constructing each state grade cloud model according to the cloud interval and the combination weight vector of each state evaluation index; each state level cloud model is an improved cloud model based on a 2En rule;
and determining the state grade of the sighting telescope system according to the membership degree.
Optionally, before calculating the cloud center of gravity position according to the combination weights of the index data to be evaluated and the state evaluation indexes, the method further includes determining the combination weights of the state evaluation indexes by using a combination weighting method combining an improved fuzzy analytic hierarchy process and an improved entropy weighting method:
determining subjective weight of the state evaluation index by adopting an improved fuzzy analytic hierarchy process; the improved fuzzy analytic hierarchy process is to change nine scales of the fuzzy analytic hierarchy process into three scales;
calculating the objective weight of the state evaluation index by using an improved entropy weight method;
establishing an optimization model for improving a combined weighting method according to the subjective weight and the objective weight; the optimization model of the improved combination weighting method is obtained by introducing an augmented Lagrangian function method on the basis of the combination weighting method;
and obtaining the combination weight of each state evaluation index according to the optimization model.
Optionally, the improved weight formula of the improved entropy weight method is as follows:
wherein w is j ' is the objective weight of the j-th index; e (E) j For the j-th information entropy, E k Is the kth information entropy; m is the number of operation data.
Optionally, the formula of the optimization model of the improved combination weighting method is as follows:
wherein a is c For the combined weight coefficient, l is the number of the combined weight coefficients, w b ,w c The weight values of the individual indexes in the principal and objective weight vectors are respectively, and lambda is the Lagrange multiplier.
Optionally, before calculating the cloud center of gravity position according to the combination weight of each index data to be evaluated and each state evaluation index, the method further includes determining a clouding interval of each state evaluation index at each state level:
acquiring sample index data of each state index;
performing cluster analysis on the sample index data by using a self-organizing map neural network algorithm, and determining the threshold value of each state evaluation index;
and determining the clouding interval of each state evaluation index in each state level according to the threshold value of each state evaluation index.
Optionally, before calculating the membership degree between the cloud center of gravity and the cloud model of each state level according to the cloud center of gravity position, the method further includes:
according to the clouding interval and the combination weight vector, constructing a cloud model of each state level of the sighting telescope system;
the parameter calculation formula of the cloud model is as follows:
wherein o is the equipment health status level; e, e o A threshold value corresponding to the equipment health state level o; ex (x) o ,En o ,He o The expected entropy and the super entropy required for constructing the evaluation cloud of the grade o are respectively obtained.
Optionally, the calculation formula for evaluating the state level is:
wherein x is a Is the position of the center of gravity of the cloud; mu (mu) o (x a ) Is x a Membership degree with corresponding state grade of o; r is the evaluation cloud x a The number of cloud drops at the position; mu (mu) r Is the membership degree of cloud drops r; en is provided with r Entropy corresponding to cloud drop r; he is x a Super entropy at the point, and represents uncertainty of the evaluation result.
The application also provides a state evaluation system of the sighting telescope system, which comprises:
the to-be-evaluated index data acquisition module is used for acquiring to-be-evaluated index data of all state evaluation indexes of the sighting telescope system;
the cloud center-of-gravity position calculation module is used for calculating the cloud center-of-gravity position according to the combination weight of each index data to be evaluated and each state evaluation index; the combination weight of each state evaluation index is determined by a combination weighting method combining an improved fuzzy analytic hierarchy process and an improved entropy weighting method; the cloud center of gravity position is the position of the cloud center of gravity in a clouding section of the state grade; the clouding interval is determined by the threshold value of each state evaluation index, and the threshold value of each state evaluation index is obtained by carrying out cluster analysis on sample index data of each state evaluation index by using a self-organizing map neural network algorithm;
the membership calculation module is used for calculating membership of the cloud center of gravity and the cloud model of each state level according to the cloud center of gravity position; constructing each state grade cloud model according to the cloud interval and the combination weight vector of each state evaluation index; each state level cloud model is an improved cloud model based on a 2En rule;
and the state grade determining module is used for determining the state grade of the sighting telescope system according to the membership degree.
Optionally, the system further comprises:
and the combination weight determining module is used for determining the combination weight of each state evaluation index by utilizing a combination weighting method combining an improved fuzzy analytic hierarchy process and an improved entropy weighting method before calculating the cloud center of gravity position according to the combination weight of each index data to be evaluated and each state evaluation index.
Optionally, the system further includes a clouding section determining module, configured to determine, before calculating the cloud center of gravity position according to the combination weights of the to-be-evaluated index data and the state evaluation indexes, a clouding section of each state evaluation index at each state level.
According to the specific embodiment provided by the application, the application discloses the following technical effects:
the application provides a state evaluation method and a state evaluation system of a sighting telescope system, wherein first, to-be-evaluated index data of each state evaluation index of the sighting telescope system is obtained; calculating the position of the center of gravity of the cloud according to the combination weight of each index data to be evaluated and each state evaluation index; calculating membership degrees of the cloud center of gravity and the cloud models of all state levels according to the cloud center of gravity position; and determining the state grade of the sighting telescope system according to the membership degree. According to the scheme, on one hand, the problem of complex signals of the sighting telescope system is considered, and the weight of each index of the system is determined by adopting a combined weighting method, so that the accuracy of weight calculation can be improved. On the other hand, by establishing an SOM neural network to cluster the system operation data, determining each index threshold according to the clustering result, and further determining the cloud interval of the cloud model, compared with a method for determining the index threshold through expert evaluation, the accuracy of the index threshold can be improved, and further the accuracy of the evaluation result is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a state evaluation method of a telescope system according to embodiment 1 of the present application;
fig. 2 is a state evaluation index chart provided in embodiment 1 of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The application aims to provide a state evaluation method and a state evaluation system of a sighting telescope system, which improve the accuracy of state evaluation of the sighting telescope system.
In order that the above-recited objects, features and advantages of the present application will become more readily apparent, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description.
Example 1
The present embodiment provides a state evaluation method of a telescope system, please refer to fig. 1, including:
s1, acquiring to-be-evaluated index data of each state evaluation index of the sighting telescope system.
The state evaluation of the telescope system includes a plurality of evaluation indexes, and in this embodiment, each index of the torque motor in the telescope system during the collision of the upper reflector is described as an example, and referring to fig. 2, each index of the torque motor during the collision of the upper reflector may also be used to evaluate a plurality of indexes such as a power signal, a voltage signal, and a control signal of the telescope system.
Index data i= [ I ] acquired in the present embodiment 1 ,I 2 ,I 3 ,...,I 12 ]。
S2, calculating the position of the center of gravity of the cloud according to the combination weight of each index data to be evaluated and each state evaluation index; the combination weight of each state evaluation index is determined by a combination weighting method combining an improved fuzzy analytic hierarchy process and an improved entropy weighting method; the cloud center of gravity position is the position of the cloud center of gravity in a clouding section of the state grade; the clouding section is determined by the threshold value of each state evaluation index, and the threshold value of each state evaluation index is obtained by carrying out cluster analysis on sample index data of each state evaluation index by using a self-organizing map neural network algorithm.
And calculating the center of gravity position of the cloud according to x=i×w, wherein X is a combination weight, and I is index data.
S3, calculating membership degrees of the cloud center and the cloud models of all state levels according to the cloud center of gravity position; constructing each state grade cloud model according to the cloud interval and the combination weight vector of each state evaluation index; each state level cloud model is an improved cloud model based on the 2En rule.
S4, determining the state grade of the sighting telescope system according to the membership degree.
As an alternative embodiment, before S2, the method further includes: and determining the combination weight of each state evaluation index by utilizing a combination weighting method combining the improved fuzzy analytic hierarchy process and the improved entropy weighting method.
The method for determining the combination weight of each state evaluation index by utilizing the combination weighting method combining the improved fuzzy analytic hierarchy process and the improved entropy weighting method specifically comprises the following steps:
determining subjective weight of the state evaluation index by adopting an improved fuzzy analytic hierarchy process; the improved fuzzy analytic hierarchy process is to change nine scales of the fuzzy analytic hierarchy process into three scales.
And calculating the objective weight of the state evaluation index by using an improved entropy weight method.
Establishing an optimization model for improving a combined weighting method according to the subjective weight and the objective weight; the optimization model of the improved combination weighting method is obtained by introducing an augmented Lagrangian function method on the basis of the combination weighting method.
And obtaining the combination weight of each state evaluation index according to the optimization model.
Wherein, the improved fuzzy consistency judgment matrix R= (R) of the improved fuzzy analytic hierarchy process (improved FAHP algorithm) aj ) n×n The method comprises the following steps:
in the above, f aj The values obtained based on the three-scale method according to the index a and the index j are shown in table 1, and n is the number of the system indexes.
Table 1 comparative values
Will r= (R ij ) n×n Conversion to a reciprocal matrix e= (E) ij ) n×n The weight vector W is calculated by normalization method (0) The calculation formula is as follows:
wherein,for the weight vector W (0) The subjective weight of the nth index is used for W through a eigenvalue method (0) Further computing more accurate weight vectors through iteration.
The weight calculation formula of the original entropy weight method is as follows:
in this embodiment, considering that the original entropy weight method calculates the weight, there is a weight distortion problem (i.e. when the entropy value of a certain index approaches 1, multiple changes of the entropy weight are caused, and when the entropy value is 1, the weight can be in the case of not being 0, which is not in agreement with the entropy weight method theory), and a weight calculation method for improving the entropy weight method is provided.
Standard matrix p= (P) of the improved entropy weight method (improved EWM algorithm) ij ) n×m The method comprises the following steps:
wherein q is ij For the ith actual value of the jth index, n is the number of system indexes, m is the number of operation data, and the information entropy of the evaluation index is calculated according to the following calculation formula:
wherein E is j And determining the weight for the j-th information entropy through improving a weight formula according to the information entropy.
Optionally, the improved weight formula is:
wherein w is j ' being an objective weight of the jth index, E k Is the kth information entropy.
The optimization model of the combined weighting method is as follows:
wherein a is c For the combined weight coefficient, l is the number of the combined weight coefficients, w b ,w c The weight values of the individual indexes in the principal and objective weight vectors are respectively.
The embodiment adopts an optimization model of a combined weighting method based on an improved game theory, specifically introduces an augmented Lagrangian function method on the basis of the combined weighting method, converts constraint problems into unconstrained problems, and obtains the optimization model of the improved combined weighting method.
As an alternative embodiment, the formula of the optimization model of the improved combination weighting method is:
wherein a is c For the combined weight coefficient, l is the number of the combined weight coefficients, w b ,w c The weight values of the individual indexes in the principal and objective weight vectors are respectively, and lambda is the Lagrange multiplier.
On the basis, the combination coefficients when the number of the combination coefficients is 2 can be obtained by solving the deviation and the extremum condition are as follows:
wherein w is 1 ,w 2 Respectively a principal and an objective weight vector,the final weights of the indexes can be further obtained by combining weights of the vector under the normalized principal and objective weights:
wherein w is * Is the final weight vector for each index.
As an optional implementation manner, before the step S2, the method further includes determining a clouding interval of each state evaluation index at each state level.
The determining the clouding interval of each state evaluation index in each state level specifically comprises the following steps:
acquiring sample index data of each state index;
performing cluster analysis on the sample index data by using a self-organizing map neural network algorithm, and determining the threshold value of each state evaluation index;
and determining the clouding interval of each state evaluation index in each state level according to the threshold value of each state evaluation index.
Wherein, the formula of the self-organizing map neural network algorithm (SOM algorithm) is as follows:
wherein w is d For the initial weight vector of the contention layer, σ 0 Radius of topological neighborhood, eta 0 For the initial rate of learning to be the same,w d(x) for the weight vector of the winning neuron, T is the current training times, T is the total training times, N (T), eta (T) and sigma (T) are respectively trained for T times, and the updated central topological neighborhood, learning rate and topological neighborhood radius, w z (t) is the neuron weight in the updated winning topology neighborhood, x g And finally judging whether the data is converged or not for the g-th input data. And ending training if the preset iteration times are reached, otherwise, performing the next training.
The cloud intervals of each state level determined in this embodiment are shown in table 2:
TABLE 2 cloud interval definition of State classes
And a, b, c and d are thresholds for determining the state level of each index by the SOM neural network cluster.
As an alternative embodiment, before the step S3, the method further includes: and constructing a cloud model of each state level of the sighting telescope system according to the clouding interval and the combination weight vector.
The method for determining 3 digital characteristic parameters of the improved cloud model based on the 2En rule comprises the following steps:
wherein o is the equipment health status level; e, e o A threshold value corresponding to the equipment health state level o; ex (x) o ,En o ,He o The expected entropy and the super entropy required for constructing the evaluation cloud of the grade o are respectively obtained.
Through the constructed cloud model, the calculation formula for evaluating the state grade is as follows:
wherein x is a Is the position of the center of gravity of the cloud; mu (mu) o (x a ) Is x a Membership degree with corresponding state grade of o; r is the evaluation cloud x a The number of cloud drops at the position; mu (mu) r Is the membership degree of cloud drops r; en is provided with r Entropy corresponding to cloud drop r; he is x a Super entropy at the point, and represents uncertainty of the evaluation result.
According to the state evaluation method of the sighting telescope system, on one hand, the problem that signals of the sighting telescope system are complex is considered, and the weight of each index of the sighting telescope system is determined by adopting a combined weighting method. On the other hand, aiming at the problem that the prior method mainly determines index thresholds through expert evaluation, an SOM neural network is established to cluster system operation data, and each index threshold is determined according to a clustering result and used for determining a clouding section of a cloud model. Meanwhile, the continuity and the ambiguity of the adjacent states are considered, a state evaluation model is built through improving the cloud model, and super entropy is introduced for evaluation grade result judgment of the sighting telescope system in the health state grade. In summary, the state evaluation method provided by the embodiment can accurately, efficiently and objectively evaluate the health state of the sighting telescope system.
Example 2
The present embodiment provides a state evaluation system of a scope system, including:
the to-be-evaluated index data acquisition module is used for acquiring to-be-evaluated index data of all state evaluation indexes of the sighting telescope system;
the cloud center-of-gravity position calculation module is used for calculating the cloud center-of-gravity position according to the combination weight of each index data to be evaluated and each state evaluation index; the combination weight of each state evaluation index is determined by a combination weighting method combining an improved fuzzy analytic hierarchy process and an improved entropy weighting method; the cloud center of gravity position is the position of the cloud center of gravity in a clouding section of the state grade; the clouding interval is determined by the threshold value of each state evaluation index, and the threshold value of each state evaluation index is obtained by carrying out cluster analysis on sample index data of each state evaluation index by using a self-organizing map neural network algorithm;
the membership calculation module is used for calculating membership of the cloud center of gravity and the cloud model of each state level according to the cloud center of gravity position; constructing each state grade cloud model according to the cloud interval and the combination weight vector of each state evaluation index; each state level cloud model is an improved cloud model based on a 2En rule;
and the state grade determining module is used for determining the state grade of the sighting telescope system according to the membership degree.
In some embodiments, the system further comprises:
and the combination weight determining module is used for determining the combination weight of each state evaluation index by utilizing a combination weighting method combining an improved fuzzy analytic hierarchy process and an improved entropy weighting method before calculating the cloud center of gravity position according to the combination weight of each index data to be evaluated and each state evaluation index.
In some embodiments, the system further includes a clouding interval determining module, configured to determine, before calculating the cloud center of gravity position according to the combined weight of each of the index data to be evaluated and each of the state evaluation indexes, a clouding interval of each of the state evaluation indexes at each of the state levels.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present application have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present application and the core ideas thereof; also, it is within the scope of the present application to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the application.
Claims (4)
1. A method of evaluating the state of a telescope system, comprising:
acquiring index data to be evaluated of each state evaluation index of the sighting telescope system;
calculating the position of the center of gravity of the cloud according to the combination weight of each index data to be evaluated and each state evaluation index; the combination weight of each state evaluation index is determined by a combination weighting method combining an improved fuzzy analytic hierarchy process and an improved entropy weighting method; the cloud center of gravity position is the position of the cloud center of gravity in a clouding section of the state grade; the clouding interval is determined by the threshold value of each state evaluation index, and the threshold value of each state evaluation index is obtained by carrying out cluster analysis on sample index data of each state evaluation index by using a self-organizing map neural network algorithm;
calculating membership degrees of the cloud center of gravity and the cloud models of all state levels according to the cloud center of gravity position; constructing each state grade cloud model according to the cloud interval and the combination weight vector of each state evaluation index; each state level cloud model is an improved cloud model based on a 2En rule;
determining the state grade of the sighting telescope system according to the membership;
wherein before calculating the cloud center of gravity position according to the combination weight of each index data to be evaluated and each state evaluation index, the method further comprises:
determining the combination weight of each state evaluation index by utilizing a combination weighting method combining an improved fuzzy analytic hierarchy process and an improved entropy weighting method:
determining subjective weight of the state evaluation index by adopting an improved fuzzy analytic hierarchy process; the improved fuzzy analytic hierarchy process is to change nine scales of the fuzzy analytic hierarchy process into three scales;
calculating the objective weight of the state evaluation index by using an improved entropy weight method;
establishing an optimization model for improving a combined weighting method according to the subjective weight and the objective weight; the optimization model of the improved combination weighting method is obtained by introducing an augmented Lagrangian function method on the basis of the combination weighting method;
obtaining the combination weight of each state evaluation index according to the optimization model;
before calculating the cloud center of gravity position according to the combination weight of each index data to be evaluated and each state evaluation index, the method further comprises determining a clouding interval of each state evaluation index in each state level:
acquiring sample index data of each state index;
performing cluster analysis on the sample index data by using a self-organizing map neural network algorithm, and determining the threshold value of each state evaluation index;
according to the threshold value of each state evaluation index, determining the clouding interval of each state evaluation index in each state level;
before calculating the membership degree of the cloud center and the cloud model of each state level according to the cloud center of gravity position, the method further comprises:
according to the clouding interval and the combination weight vector, constructing a cloud model of each state level of the sighting telescope system;
the parameter calculation formula of the cloud model is as follows:
wherein o is the equipment health status level; e, e o A threshold value corresponding to the equipment health state level o; ex (x) o ，En o ，He o The expected entropy and the super entropy required by constructing the evaluation cloud of the class o are respectively;
the calculation formula for evaluating the state grade is:
wherein x is a Is the position of the center of gravity of the cloud; mu (mu) o (x a ) Is x a Membership degree with corresponding state grade of o; r is the evaluation cloud x a Cloud of placesThe number of drops; mu (mu) r Is the membership degree of cloud drops r; en is provided with r Entropy corresponding to cloud drop r; he is x a Super entropy at the point, and represents uncertainty of the evaluation result.
2. The method of claim 1, wherein the improved weight formula of the improved entropy weight method is:
wherein w is j ' is the objective weight of the j-th index; e (E) j For the j-th information entropy, E k Is the kth information entropy; m is the number of operation data.
3. The method of claim 1, wherein the formula for the optimization model for improved combined weighting is:
wherein a is c For the combined weight coefficient, l is the number of the combined weight coefficients, w b ,w c The weight values of the individual indexes in the principal and objective weight vectors are respectively, and lambda is the Lagrange multiplier.
4. A state evaluation system of a scope system, comprising:
the to-be-evaluated index data acquisition module is used for acquiring to-be-evaluated index data of all state evaluation indexes of the sighting telescope system;
the cloud center-of-gravity position calculation module is used for calculating the cloud center-of-gravity position according to the combination weight of each index data to be evaluated and each state evaluation index; the combination weight of each state evaluation index is determined by a combination weighting method combining an improved fuzzy analytic hierarchy process and an improved entropy weighting method; the cloud center of gravity position is the position of the cloud center of gravity in a clouding section of the state grade;
the clouding interval is determined by the threshold value of each state evaluation index, and the threshold value of each state evaluation index is obtained by carrying out cluster analysis on sample index data of each state evaluation index by using a self-organizing map neural network algorithm;
the membership calculation module is used for calculating membership of the cloud center of gravity and the cloud model of each state level according to the cloud center of gravity position; constructing each state grade cloud model according to the cloud interval and the combination weight vector of each state evaluation index; each state level cloud model is an improved cloud model based on a 2En rule;
the state grade determining module is used for determining the state grade of the sighting telescope system according to the membership degree;
the combination weight determining module is used for determining the combination weight of each state evaluation index by utilizing a combination weighting method combining an improved fuzzy analytic hierarchy process and an improved entropy weighting method before calculating the position of the center of gravity of the cloud according to the combination weight of each index data to be evaluated and each state evaluation index; determining subjective weight of the state evaluation index by adopting an improved fuzzy analytic hierarchy process; the improved fuzzy analytic hierarchy process is to change nine scales of the fuzzy analytic hierarchy process into three scales; calculating the objective weight of the state evaluation index by using an improved entropy weight method; establishing an optimization model for improving a combined weighting method according to the subjective weight and the objective weight; the optimization model of the improved combination weighting method is obtained by introducing an augmented Lagrangian function method on the basis of the combination weighting method; obtaining the combination weight of each state evaluation index according to the optimization model;
the clouding interval determining module is used for determining the clouding interval of each state evaluation index in each state grade before calculating the position of the center of gravity of the cloud according to the combination weight of each index data to be evaluated and each state evaluation index;
specifically, sample index data of each state index is obtained; performing cluster analysis on the sample index data by using a self-organizing map neural network algorithm, and determining the threshold value of each state evaluation index; according to the threshold value of each state evaluation index, determining the clouding interval of each state evaluation index in each state level;
before calculating the membership degree of the cloud center and the cloud model of each state level according to the cloud center of gravity position, the system further comprises:
according to the clouding interval and the combination weight vector, constructing a cloud model of each state level of the sighting telescope system;
the parameter calculation formula of the cloud model is as follows:
wherein o is the equipment health status level; e, e o A threshold value corresponding to the equipment health state level o; ex (x) o ，En o ，He o The expected entropy and the super entropy required by constructing the evaluation cloud of the class o are respectively;
the calculation formula for evaluating the state grade is:
wherein x is a Is the position of the center of gravity of the cloud; mu (mu) o (x a ) Is x a Membership degree with corresponding state grade of o; r is the evaluation cloud x a The number of cloud drops at the position; mu (mu) r Is the membership degree of cloud drops r; en is provided with r Entropy corresponding to cloud drop r; he is x a Super entropy at the point, and represents uncertainty of the evaluation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211403115.6A CN115618743B (en) | 2022-11-10 | 2022-11-10 | State evaluation method and state evaluation system of sighting telescope system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211403115.6A CN115618743B (en) | 2022-11-10 | 2022-11-10 | State evaluation method and state evaluation system of sighting telescope system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115618743A CN115618743A (en) | 2023-01-17 |
| CN115618743B true CN115618743B (en) | 2023-11-14 |
Family
ID=84879096
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211403115.6A Active CN115618743B (en) | 2022-11-10 | 2022-11-10 | State evaluation method and state evaluation system of sighting telescope system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115618743B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117933098A (en) * | 2024-03-21 | 2024-04-26 | 沈阳顺义科技股份有限公司 | Aeroengine health assessment method based on oil analysis |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046453A (en) * | 2015-09-02 | 2015-11-11 | 中铁十一局集团有限公司 | Construction engineering project cluster establishment method introducing cloud model for evaluation and selection |
| CN114065495A (en) * | 2021-11-09 | 2022-02-18 | 国网宁夏电力有限公司电力科学研究院 | Transformer state evaluation method based on reverse cloud combination weight and fuzzy closeness |
-
2022
- 2022-11-10 CN CN202211403115.6A patent/CN115618743B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046453A (en) * | 2015-09-02 | 2015-11-11 | 中铁十一局集团有限公司 | Construction engineering project cluster establishment method introducing cloud model for evaluation and selection |
| CN114065495A (en) * | 2021-11-09 | 2022-02-18 | 国网宁夏电力有限公司电力科学研究院 | Transformer state evaluation method based on reverse cloud combination weight and fuzzy closeness |
Non-Patent Citations (2)
| Title |
|---|
| 基于组合赋权和云模型的风电机组健康状态评估;董兴辉;张鑫淼;郑凯;王帅;;太阳能学报(第08期);全文 * |
| 解宝琦等.《一种坦克炮长瞄准镜系统状态评估的方法》.《兵工学报》.2022,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115618743A (en) | 2023-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108038300B (en) | Optical fiber state evaluation method based on improved membership function combined with neural network | |
| CN102496069B (en) | Cable multimode safe operation evaluation method based on fuzzy analytic hierarchy process (FAHP) | |
| CN105117602B (en) | A kind of metering device running status method for early warning | |
| CN110334875A (en) | Meter and the wind power combined probability prediction technique of evaluation index conflict | |
| CN111144552B (en) | Multi-index grain quality prediction method and device | |
| CN106656357B (en) | Power frequency communication channel state evaluation system and method | |
| CN116150897A (en) | Machine tool spindle performance evaluation method and system based on digital twin | |
| CN115114128B (en) | Satellite health state evaluation system and satellite health state evaluation method | |
| CN106971241B (en) | Method for predicting sewage quality data based on fuzzy neural network | |
| CN115618743B (en) | State evaluation method and state evaluation system of sighting telescope system | |
| CN115564114A (en) | Short-term prediction method and system for airspace carbon emission based on graph neural network | |
| CN113225346A (en) | Network operation and maintenance situation assessment method based on machine learning | |
| CN111932081B (en) | Method and system for evaluating running state of power information system | |
| CN112766603A (en) | Traffic flow prediction method, system, computer device and storage medium | |
| CN115619028A (en) | Clustering algorithm fusion-based power load accurate prediction method | |
| CN111785093A (en) | Air traffic flow short-term prediction method based on fractal interpolation | |
| CN113884807A (en) | Power distribution network fault prediction method based on random forest and multi-layer architecture clustering | |
| CN109684713A (en) | Bayes-based complex system reliability analysis method | |
| CN113033898A (en) | Electrical load prediction method and system based on K-means clustering and BI-LSTM neural network | |
| CN113298296A (en) | Method for predicting day-ahead load probability of power transmission substation from bottom to top | |
| CN105117559A (en) | Firearm design scheme evaluation method based on fuzzy decision diagram and gray correlation analysis | |
| WO2023061303A1 (en) | Large-scale fading modeling and estimation method, system, and device, and storage medium | |
| CN108668254B (en) | WiFi signal characteristic area positioning method based on improved BP neural network | |
| CN112561203B (en) | Method and system for realizing water level early warning based on clustering and GRU | |
| CN115236616A (en) | Radar system quality determination method and system based on combined weighted gray cloud model |
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 | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: No. 23 Kaifa Road, Shenyang Economic and Technological Development Zone, Shenyang City, Liaoning Province, 110027 Patentee after: Shenyang Shunyi Technology Co.,Ltd. Country or region after: China Address before: 110027 No.27, 16th Street, Shenyang Economic and Technological Development Zone, Liaoning Province Patentee before: SHENYANG SHUNYI TECHNOLOGY Co.,Ltd. Country or region before: China |