CN108776855A - A kind of smart machine health status evaluation method and system - Google Patents

Abstract

The present invention provides a method and system for evaluating the health status of smart devices. The method includes: acquiring information about the running status of equipment; The relationship between the influencing factors obtains the equipment health status; the intelligent equipment health status evaluation index system model includes: a target layer and a layered criterion layer based on the relationship between the equipment health status influencing factors; the technical solution provided by the invention obtains the equipment health status , the maintenance department arranges maintenance tasks according to the health status of the equipment, and gives priority to dealing with equipment defects in critical states, which can greatly improve the efficiency of operation and maintenance, and at the same time ensure the safe operation of the power grid.

Description

A method and system for evaluating the health state of an intelligent device

technical field

The invention relates to a method for evaluating the health state of an intelligent device, in particular to a method and system for evaluating the health state of an intelligent device.

Background technique

Intelligent equipment is the main component of the substation secondary system and its electrical circuit. For a long time, as an electronic device that monitors, controls, regulates and protects the primary system, the analysis of the operating status data of smart devices has not been taken seriously, and only part of the device self-test information is output. The equipment maintenance mechanism mainly includes planned maintenance, post-event maintenance and predictive maintenance. Planned maintenance has caused a lot of waste of resources and equipment, and subsequent maintenance has brought unpredictable safety hazards to the power system, which can no longer meet the requirements of intelligent production. However, due to the limited information collected on the operation of smart devices, predictive maintenance of smart devices has not been carried out.

At present, non-linear and fuzzy processing methods are often used in the evaluation of intelligent equipment. Such methods have limited samples, complex algorithms, and incomplete evaluation basis. They are usually used to evaluate the health status of large-scale electromechanical equipment with many uncertain evaluation index factors.

Contents of the invention

In order to solve the above-mentioned deficiencies in the prior art, the present invention provides a method for evaluating the health status of smart devices.

The technical scheme provided by the invention is:

A method for evaluating the health status of an intelligent device, the method comprising:

Obtain information about the running status of the standby device;

In the pre-built smart device health status evaluation index system model, the equipment health status is obtained according to the relationship between the obtained equipment operation status information and the equipment health status influencing factors;

The smart device health state evaluation index system model includes: a target layer and a layered criterion layer constructed based on the relationship between factors affecting the health state of the device.

Preferably, the construction of the equipment health state evaluation index system model includes:

Set the smart device health status as the target layer;

Constructing a first-level criterion layer based on various factors affecting the target layer, wherein each factor corresponds to a first-level indicator of the first-level criterion layer;

Based on each first-level indicator, constructing a second-level indicator of the first-level indicator according to factors affecting the first-level indicator;

All secondary indicators construct a secondary criterion layer;

Preferably, each index of the first-level criterion layer and the second-level criterion layer includes a weight;

Based on the relationship between the first-level indicators, the weight matrix of the first-level criterion layer is established, wherein each first-level indicator is a first-level weight vector;

Based on the scope of the weight vectors of each of the first-level indicators, and the relationship between the second-level indicators under each first-level indicator, the weight matrix of the second-level indicators under the first-level indicators is constructed; wherein, each second-level indicator is a Vector of secondary weights.

Preferably, the obtaining of the equipment health status according to the relationship between the obtained equipment operation status information and the influencing factors of the equipment health status in the pre-built smart equipment health status evaluation index system model includes:

Scoring the secondary indicators within the scope of the weight vector based on the equipment operation status information and the secondary indicators;

Calculate the score of each first-level indicator by using the normalization method to calculate the score of the second-level indicator;

Calculate the health score of the smart device by using the normalization method to calculate the score of the first-level index;

Determine the health status of the device based on the health score combined with the preset health status table.

Preferably, a normalization method is used to calculate the health score of the smart device:

In the formula, HF is the health score of the tested smart device; m is the element number after the normalization of the compared elements; It is the score of the secondary indicator.

Preferably, the secondary weight vector is calculated as follows:

ω _m = ω _A [i]*ω _m

Among them, ω _m : secondary weight vector; i: 0, 1, 2, 3 or 4; ω _A : relative weight of elements sorted under the target layer.

Preferably, the first-level weight vector is calculated as follows:

Aω _A = λ _maxA ω _A

Among them, ω _A : the relative weight of the elements sorted under the target layer; A: judgment matrix, the judgment matrix A is obtained by combining the impact level of the health status index of the smart device and the Satty 1-9 value method; λ _maxA : the maximum eigenvalue of the matrix A.

Preferably, the device operation status information includes: communication status, external environment, device resources, self-check information and time synchronization status;

The communication status includes: SV communication status, GOOSE communication status and station control layer communication status;

The external environment: including the internal temperature of the chassis and the AC and DC power supply voltage;

The device resources: including CPU temperature and load, CPU operating voltage, communication optical port power, memory usage and disk storage space;

The self-inspection information: including device hardware self-inspection, fixed value verification, AC input circuit monitoring and secondary circuit monitoring;

The time synchronization state: includes time synchronization signal state, time synchronization service state and time jump.

Preferably, the determining the health status of the device according to the health score combined with the preset health status table includes:

If the health score of the device is 100, the device is in a healthy state;

If 85≤device health score<100, the device is in a dangerous state;

If the health status score of the device is less than 85, the device is in a critical state.

Preferably, the equipment health state evaluation index system model further includes: a scheme layer;

The solution layer includes: when the health state of the smart device at the target layer is not in a healthy state, various alternative measures are constructed based on the common problems of the first-level index and the second-level index in order to make the state of the smart device at the target layer reach a healthy state , Decision-making plan.

A system for evaluating the health status of intelligent equipment, the system comprising:

The equipment information acquisition module is used to acquire the equipment operation status information;

The health state determination module is used to input the obtained equipment operation state information into the pre-built intelligent equipment health state evaluation index system model to obtain the equipment health state according to the relationship between the obtained equipment operation state information and the influencing factors of the equipment health state.

Preferably, it also includes: a model building module: used to build the smart device health status evaluation index system model;

The smart device health status evaluation index system model includes: the target layer and the layered criterion layer based on the relationship between the factors affecting the health status of the device.

Preferably, the model building blocks include:

Target layer determination sub-module: used to determine the target layer based on the health status of smart devices;

Criterion layer determination sub-module: used to determine the criterion layer according to various factors affecting the target layer and the mutual influence between each factor.

Preferably, the determination criterion layer submodule includes:

The first determining unit is configured to construct a first-level criterion layer based on various factors affecting the target layer, wherein each factor corresponds to a first-level indicator of the first-level criterion layer;

The second determining unit is configured to construct secondary indicators of the first-level indicators based on each first-level indicator according to factors affecting the first-level indicators;

Preferably, the health status determination module includes:

A scoring sub-module, configured to score the secondary indicators based on the equipment operation status information and the weight vector range of the secondary indicators;

The calculation sub-module is used to calculate the score of each first-level indicator and the health score of the smart device;

The scores of the first-level indicators include: the scores of the second-level indicators are calculated using a normalization method to obtain the scores of each first-level indicator;

The score of the first-level indicator includes: the score of the first-level indicator is calculated by a normalization method to obtain the health score of the smart device;

The determination sub-module is used to determine the health status of the device according to the health score and the preset health status table.

Compared with prior art, the beneficial effect of the present invention is:

1. The present invention proposes a method for quantitative evaluation of equipment health status, which obtains equipment operation status information; in the pre-built intelligent equipment health status evaluation index system model, according to the acquired equipment operation status information and equipment health status influencing factors The health status evaluation index system model of smart equipment includes: the target layer and the layered criterion layer based on the relationship between the factors affecting the health status of equipment; it solves the problem that the evaluation basis for the health status evaluation of large electromechanical equipment is not comprehensive The health status assessment of large-scale electromechanical equipment with many uncertain evaluation index factors can be carried out.

2. The technical solution provided by the present invention can quantitatively evaluate the health status of smart devices, and use this as a basis for condition-based maintenance to distinguish critical states, dangerous states, and healthy states of smart devices, and solve the problem of a large number of resources and equipment caused by planned maintenance. Waste and after-the-fact maintenance bring unpredictable safety hazards to the power system.

3. The technical solution provided by the present invention enables the maintenance department to arrange maintenance tasks according to the health status of the equipment, give priority to dealing with critical state equipment defects, and then deal with dangerous state equipment defects that are not critical to system safety, which can greatly improve the operation and maintenance efficiency, and at the same time guarantee safe operation of the grid.

Description of drawings

Fig. 1 is a flow chart of the smart device health status evaluation method of the present invention;

Fig. 2 is a schematic structural diagram of the smart device health status evaluation system of the present invention;

Fig. 3 is a schematic diagram of a model of the smart device health status evaluation system of the present invention.

Detailed ways

In order to better understand the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, and Not all examples. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

Example 1:

A method and system for quantitative evaluation of equipment health status provided by the present invention, as shown in Figure 1:

Input the obtained equipment operation status information into the pre-built intelligent equipment health status evaluation index system model to obtain the equipment health status;

The smart device health status evaluation index system model includes: target layer, criterion layer and program layer.

The intelligent substation adopts the IEC 61850 standard, network sampling and control technology, and embedded intelligent equipment. The information collection is digitized and the communication is networked. Free interoperability, there is no problem in online monitoring information interaction. Therefore, the intelligent equipment condition monitoring system can uniformly collect most of the information that reflects the operating condition of the equipment, including state quantity and quantity measurement.

According to the equipment operation status information, the establishment of a tree-like hierarchical structure model is to analyze the relationship, logical attribution and importance of each indicator in the system, and arrange them hierarchically to form a top-down ladder hierarchical structure. The weight of each element in the model evaluation is determined by the AHP method, and the tree-like hierarchical structure model is the smart device health status evaluation index system model.

1. The health status evaluation index system model of smart equipment, as shown in Figure 3:

The smart device health status evaluation index system model is a hierarchical evaluation model, which can be roughly divided into three levels:

(1) Target layer: There is only one element, that is, the health status index evaluation system of smart devices.

(2) Criterion layer: It includes the intermediate links involved in realizing the health of the smart device state.

The operating status information of smart devices includes five aspects: communication status, external environment, device resources, self-inspection information, and time synchronization status. These five aspects are selected as the first-level criterion layer evaluation indicators for measuring the health status of equipment. Each first-level criterion layer is further divided into several second-level criterion layers.

Communication status: Including SV communication status, GOOSE communication status and station control layer communication status three secondary criterion layer indicators.

External environment: Including the internal temperature of the chassis and the AC and DC power supply voltage, two second-level criteria layer indicators.

Device resources: Including CPU temperature and load, CPU operating voltage, communication optical port power, memory usage, and disk storage space, five secondary criterion layer indicators.

Self-inspection information: including four secondary criterion layer indicators of device hardware self-inspection, fixed value verification, AC input circuit monitoring and secondary circuit monitoring.

Time Synchronization Status: Including the time synchronization signal status, time synchronization service status and time jump three criteria layer indicators.

(3) Scheme layer: It includes various measures and decision-making schemes that can be selected to achieve the goal, that is, whether the operating status of the smart device meets the requirements of the impact indicators involved in the status and health of the smart device at the criterion layer.

2. Judgment matrix of each level

The hierarchy reflects the relationship between indicators, but the weight of each criterion in the criterion is not necessarily the same in the target measurement. The AHP provides 1-9 scaling methods to represent the importance of different indicators. Assuming to compare the influence of n elements Y={y ₁ ,y ₂ ,y ₃ ,,y _n } on the target, two elements y _i and y _j are taken each time, then the element a _ij of the judgment matrix A represents y The ratio of the degree of influence of _i and y _j on the target, where the value of a _ij is determined by the Satty 1-9 value method. When a _ij >1, the index i is more important than j for the target, and its numerical value represents the degree of importance. At the same time, there must be a _ji =(1/a _ij )<1, the index j is less important than the index i for the target, and its numerical value indicates the degree of unimportance. Therefore, the judgment matrix is a positive and negative matrix.

Table 1 shows the impact level of smart device health status indicators.

grade Concrete performance 5 Affect the safe operation of the smart device and thus affect the safe operation of the power grid 4 Affect the safe operation of the automation system 3 Affect device function 2 Affect equipment life 1 hardly affect

Establish a criterion layer A judgment matrix under the target layer of the smart device health status evaluation index system model, and comprehensively consider the impact of communication status, external environment, device resources, self-inspection information, and time synchronization status. The abnormality of device communication status will affect The safe operation of the power grid, the abnormality of equipment resources and self-inspection information are obviously related to the stable operation of the equipment, the abnormality of the time synchronization state may affect the safe operation of the automation system, and the defects of the external environment will not directly lead to the abnormality of the equipment function, so the communication The importance of status and time synchronization status indicators is prioritized, and the indicators of device resources and self-check information are slightly less important, and the impact of the external environment is relatively small.

The judgment matrix of the second-level criterion layer B under the first-level criterion layer B index. The abnormality of GOOSE communication status and SV communication status will affect the safe operation of the power grid. Although the abnormality of the communication network of the station control layer will affect the normal operation of the substation automation system, it will not cause serious failures such as refusal or malfunction of the equipment. Therefore, the communication status of the station control layer Indicators are slightly weaker.

The judgment matrix of the second-level criterion layer C under the index of the first-level criterion layer C. The priority of the AC and DC power supply voltage index is slightly higher than that of the internal temperature index of the chassis.

The judgment matrix of the second-level criterion layer D under the index of the first-level criterion layer D. The importance of the five indicators is basically the same.

The judgment matrix of the second criterion layer E under the index of the first criterion layer E. The importance of the four indicators is basically the same.

The judgment matrix of the second-level criterion layer F under the first-level criterion layer F index. The abnormality of the two indicators of time synchronization signal state and time synchronization service state will affect the function of the automation system, so the importance is slightly higher than the time jump index.

3. Hierarchical single sorting and consistency check

Based on the above analysis, the judgment matrices A, B, C, D, E, and F corresponding to the first-level criterion layer and the second-level criterion layer are respectively established, and the relative weight of a single criterion element is calculated from this. Under the target layer, elements A ₁ , A ₂ , A ₃ , A ₄ , and A ₅ constitute the judgment matrix A. A corresponding solution characteristic root equation Aω _A = λ _maxA ω _A , where λ _maxA is the largest eigenvalue of matrix A, and ω _A is the eigenvector corresponding to λ _maxA , indicating the relative weight of the five elements sorted under the target layer.

Take A’s normalized eigenvector ω _A =(ω ₁ ,ω ₂ ,,ω _n ) corresponding to λ _maxA , (∑ω _i =1) as index Y={y ₁ ,y ₂ ,y _n } pair The weight vector of the target. According to ω _A = (ω ₁ , ω ₂ ,, ω _n ), the size of component ω _i can rank the importance of indicators.

In order to reduce the artificial quantitative error, it is also necessary to judge the consistency of the matrix A. Consistency ratio in To judge the consistency index of matrix A, RI is the random consistency index, and RI is related to the matrix order.

Table 2 Average Stochastic Consistency Index

no 1 2 3 4 5 6 7 8 9 RI 0 0 0.58 0.90 1.12 1.24 1.32 1.41 1.45

when , A has satisfactory consistency.

In the same way, the normalized feature weight vectors of the judgment matrices B, C, D, E, and F are obtained, that is, the relative weight ordering under the corresponding criterion layer, and the consistency of each matrix is checked. If the judgment matrix does not have satisfactory consistency, adjust the matrix until it has satisfactory consistency.

Each second-level criterion layer is further subdivided under the first-level criterion layer, so the ordering of the importance of indicators by the second-level criterion layer should also consider the importance ordering of the first-level criterion layer to the factors of the second-level criterion layer.

ω _{B_final} ＝ω _A [0]*ω _B , where ω _{B_final} is the weight ranking of indicators in the second-level criterion layer B, and ω _B is the normalized feature weight vector of B.

ω _{C_final} ＝ω _A [1]*ω _C , where ω _{C_final} is the weight ranking of each indicator in the second-level criterion layer C, and ω _C is the normalized feature weight vector of C.

ω _{D_final} ＝ω _A [2]*ω _D , where ω _{D_final} is the weight ranking of each indicator in the second-level criterion layer D, and ω _D is the normalized feature weight vector of D.

ω _{E_final} ＝ω _A [3]*ω _E , where ω _{E_final} is the weight ranking of each indicator of the second-level criterion layer E, and ω _E is the normalized feature weight vector of E.

ω _{F_final} ＝ω _A [4]*ω _F , where ω _{F_final} is the weight ranking of the indicators of the second-level criterion layer F, and ω _F is the normalized feature weight vector of F.

In summary, the weight order ω _m of all matrices can be calculated as follows:

ω _m = ω _A [i]*ω _m

Among them, i: 0, 1, 2, 3 or 4; ω _A : the feature weight vector normalized by the element at the target layer.

4. Condition-based maintenance analysis and decision-making

Set the full score of the equipment health status to 100 points, if there is a certain defect, the points will be deducted, and the quantified score of the equipment health status is The device health status is divided into three statuses: healthy, dangerous and critical. If the device health status score is 100, the device is in a healthy state; if 85<device health status score<100, the device is in a dangerous state and needs to be repaired as soon as possible; if the device health status score is <85, the device is in a critical state and needs to be repaired immediately Send someone to overhaul.

Example 2:

Based on the same inventive concept, the present invention also provides a smart device health status evaluation system, as shown in Figure 2, the system includes:

A system for evaluating the health status of intelligent equipment, the system comprising:

The equipment information acquisition module is used to acquire the equipment operation status information;

The health state determination module is used to input the obtained equipment operation state information into the pre-built intelligent equipment health state evaluation index system model to obtain the equipment health state according to the relationship between the obtained equipment operation state information and the influencing factors of the equipment health state.

Preferably, it also includes: a model building module: used to build the smart device health status evaluation index system model;

The smart device health status evaluation index system model includes: the target layer and the layered criterion layer based on the relationship between the factors affecting the health status of the device.

Preferably, the model building blocks include:

Target layer determination sub-module: used to determine the target layer based on the health status of smart devices;

Criterion layer determination sub-module: used to determine the criterion layer according to various factors affecting the target layer and the mutual influence between each factor.

Preferably, the determination criterion layer submodule includes:

The first determining unit is configured to construct a first-level criterion layer based on various factors affecting the target layer, wherein each factor corresponds to a first-level indicator of the first-level criterion layer;

The second determining unit is configured to construct secondary indicators of the first-level indicators based on each first-level indicator according to factors affecting the first-level indicators;

Preferably, the health status determination module includes:

A scoring sub-module, configured to score the secondary indicators based on the equipment operation status information and the weight vector range of the secondary indicators;

The calculation sub-module is used to calculate the score of each first-level indicator and the health score of the smart device;

The scores of the first-level indicators include: the scores of the second-level indicators are calculated using a normalization method to obtain the scores of each first-level indicator;

The score of the first-level indicator includes: the score of the first-level indicator is calculated by a normalization method to obtain the health score of the smart device;

The determination sub-module is used to determine the health status of the device according to the health score and the preset health status table.

Preferably, the calculation submodule includes: a first calculation unit, which is used to calculate the health score HF according to the following formula:

In the formula, m: element number after normalization of the compared element; The score value of each index of the criterion layer;

The second calculation unit is used to calculate the weight vector of the secondary index according to the following formula:

ω _m = ω _A [i]*ω _m

Among them, ω _m : weight vector; i: 0, 1, 2, 3 or 4; ω _A : relative weight of elements sorted under the target layer;

The third calculation unit is used to calculate the weight vector of the first-level index according to the following formula:

Aω _A = λ _maxA ω _A

Among them, ω _A : the relative weight of elements sorted under the target layer; A: matrix; λ _maxA : the maximum eigenvalue of matrix A.

Preferably, the index determination submodule includes:

Communication status unit: used to obtain SV communication status, GOOSE communication status and station control layer communication status;

External environment unit: used to obtain the internal temperature of the chassis and the AC and DC power supply voltage;

Device resource unit: used to obtain CPU temperature and load, CPU operating voltage, communication optical port power, memory usage and disk storage space;

Self-inspection information unit: used to obtain device hardware self-inspection, fixed value verification, AC input circuit monitoring and secondary circuit monitoring;

Time synchronization state unit: used to obtain the time synchronization signal state, time synchronization service state and time jump.

Example 3:

The judgment matrix of the health status evaluation system of the measurement and control device is as follows:

The weight vector representing the importance ranking of indicators in the second criterion layer is:

ω _{A_final} = (0.403048, 0.0790856, 0.136731, 0.136731, 0.244403),

ω _{B_final} = (0.172735, 0.172735, 0.0575783),

ω _{C_final} = (0.0263619,0.0527238),

ω _{D_final} = (0.0273463,0.0273463,0.0273463,0.0273463,0.0273463),

ω _{E_final} = (0.0341829,0.0341829,0.0341829,0.0341829),

ω _{F_final} = (0.104744, 0.104744, 0.0349148).

An optical port of a smart substation measurement and control device generates an abnormal light intensity alarm, but the communication is normal, so the health status score of the measurement and control device is 97.3 points, which is in a dangerous state, and personnel should be arranged for maintenance in the near future; if the optical port is damaged, SV/ GOOSE link disconnection alarm, the health status score of the measurement and control device is less than 83 points, it is in a critical state, and it should be repaired immediately.

Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowcharts and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

The above are only embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention are included in the pending application of the present invention. within the scope of the claims.

Claims (12)

1. a kind of smart machine health status evaluation method, which is characterized in that the method includes：

Obtain equipment running status information；

According to the equipment running status of the acquisition in the smart machine health status assessment indicator system model built in advance Relationship between information and equipment health status influence factor obtains equipment health status；

The smart machine health status assessment indicator system model includes：Destination layer and be based on equipment health status influence factor Between relationship build layering rule layer.

2. the method as described in claim 1, which is characterized in that the structure of the equipment health status assessment indicator system model Including：

Smart machine health status is set as destination layer；

Level-one rule layer is built based on each factor for influencing destination layer, wherein each factor corresponds to the one of the level-one rule layer A first class index；

Based on each first class index, the two-level index of the first class index is built according to the influence factor to first class index；

All two-level index build two level rule layer.

3. method as claimed in claim 2, which is characterized in that the level-one rule layer and each index of two level rule layer are wrapped Include weight；

Level-one rule layer weight matrix is established based on the relationship between first class index, wherein each first class index is that a level-one is weighed Weight vector；

Relationship under the range of weight vectors based on each first class index, and each first class index between two-level index, structure Build the weight matrix of two-level index under the first class index；Wherein, each two-level index is a two level weight vectors.

4. method as claimed in claim 3, which is characterized in that described to refer in the smart machine health status built in advance evaluation It is obtained according to the relationship between the equipment running status information of the acquisition and equipment health status influence factor in mark system model Equipment health status includes：

It is the two-level index marking within the scope of weight vectors based on equipment running status information and two-level index；

The score value of two-level index is calculated to the score value of each first class index using method for normalizing；

The score value of first class index is calculated to the healthy score of smart machine using method for normalizing；

Preset health status table is combined according to healthy score, determines equipment health status.

5. method as claimed in claim 4, which is characterized in that calculate the health point of the smart machine using method for normalizing Number：

In formula, HF is the healthy score of tested smart machine；m：For the element number after being normalized by comparison element；For two level Index obatained score.

6. method as claimed in claim 3, which is characterized in that the two level weight vectors are calculated as follows：

ω_m=ω_A[i]*ω_m

Wherein, ω_m：Two level weight vectors；i：0,1,2,3 or 4；ω_A：The corresponding level-one weight vectors of the two level weight vectors Relative weighting.

7. method as claimed in claim 3, which is characterized in that the level-one weight vectors are calculated as follows：

Aω_A=λ_maxAω_A

Wherein, ω_A：The relative weighting that element sorts under destination layer；A：Judgment matrix, judgment matrix A is by smart machine health shape State Index Influence grade combination Satty 1-9 value methods obtain；λ_maxA：Matrix A maximum eigenvalue.

8. a kind of smart machine health status evaluation system, which is characterized in that the system comprises：

Apparatus information acquiring module, for obtaining standby running state information；

Health status determining module, the smart machine health for building the equipment running status information input of acquisition in advance According between the equipment running status information of the acquisition and equipment health status influence factor in state evaluation Index System Model Relationship obtain equipment health status.

9. a kind of smart machine health status evaluation system as claimed in claim 8, which is characterized in that further include：Model construction Module：For building the smart machine health status assessment indicator system model；

Smart machine health status assessment indicator system model includes：Destination layer and based on being closed between equipment health status influence factor It is the layering rule layer of structure.

10. system as claimed in claim 9, which is characterized in that the model construction module, including：

Destination layer determination sub-module：For determining destination layer based on smart machine health status；

Rule layer determination sub-module：For according to the determination that influences each other between each factor and each factor for influencing destination layer Rule layer.

11. system as claimed in claim 10, which is characterized in that the determining rule layer submodule, including：

First determination unit, for building level-one rule layer based on each factor for influencing destination layer, wherein each factor corresponds to One first class index of the level-one rule layer；

Second determination unit builds the level-one according to the influence factor to first class index and refers to for being based on each first class index Target two-level index.

12. system as claimed in claim 8, which is characterized in that the health status determining module, including：

Marking submodule, for being that the two level refers within the scope of the weight vectors based on equipment running status information and two-level index Mark marking；

Computational submodule, the healthy score of score value and smart machine for calculating each first class index；

The score value of the first class index includes：Each first class index is calculated using method for normalizing in the score value of two-level index Score value；

The score value of the first class index includes：The health of smart machine is calculated using method for normalizing for the score value of first class index Score；

Determination sub-module determines equipment health status for combining preset health status table according to healthy score.