CN112488432B - Equipment health assessment method, storage device and terminal - Google Patents
Equipment health assessment method, storage device and terminal Download PDFInfo
- Publication number
- CN112488432B CN112488432B CN201910850541.6A CN201910850541A CN112488432B CN 112488432 B CN112488432 B CN 112488432B CN 201910850541 A CN201910850541 A CN 201910850541A CN 112488432 B CN112488432 B CN 112488432B
- Authority
- CN
- China
- Prior art keywords
- equipment
- obtaining
- parameters
- degradation
- membership
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 230000036541 health Effects 0.000 title claims description 96
- 238000005315 distribution function Methods 0.000 claims abstract description 13
- 230000015556 catabolic process Effects 0.000 claims description 58
- 238000006731 degradation reaction Methods 0.000 claims description 58
- 239000013598 vector Substances 0.000 claims description 56
- 238000011156 evaluation Methods 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 23
- 238000005259 measurement Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 9
- 230000009471 action Effects 0.000 claims description 3
- 239000012634 fragment Substances 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 11
- 238000009826 distribution Methods 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 abstract 2
- 238000012217 deletion Methods 0.000 abstract 1
- 230000037430 deletion Effects 0.000 abstract 1
- 238000011002 quantification Methods 0.000 abstract 1
- 230000006399 behavior Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Game Theory and Decision Science (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a spare part safety stock calculation method, storage equipment and a terminal. Wherein the method comprises the following steps: s100, acquiring sample parameters, wherein the sample parameters comprise: death data and right deletion data; s200, obtaining a reliability distribution function according to the sample parameters, wherein the reliability distribution function is used for representing failure distribution of spare parts; s300, obtaining the posterior probability of failure of each currently working spare part in the next purchasing period according to the reliability distribution function; s400, obtaining a failure number probability distribution function according to the posterior probability; s500, acquiring service level parameters; s600, obtaining the spare part safety stock number according to the service level parameter and the failure number probability distribution function. The spare part safety stock calculation method, the storage device and the terminal provided by the invention can provide the spare part stock suggestion meeting the condition of setting the customer service level, provide a scientific quantification method for the spare part stock of enterprises, and effectively reduce the operation and maintenance cost.
Description
Technical Field
The invention belongs to the field of equipment maintenance and guarantee, and particularly relates to an equipment health assessment method, storage equipment and a terminal.
Background
The health management concept was introduced into the field of equipment maintenance and assurance in the late 80 s to the 90 s of the 20 th century. With the intensive research of equipment quality management, early comprehensive quality management concepts, namely a process-based reliability improvement method, are formed. Initially, people were mainly monitoring the "health" of the equipment using sensors and software, but engineers soon found that monitoring alone was inadequate, and what measures were taken based on the monitored parameters, so people replaced the term "monitoring" with the term "management". The equipment health state assessment is an important function of the equipment health management system, and can accurately assess the health state of the equipment, so that not only can the basis be provided for fault prediction and maintenance decision of the equipment, but also technical support can be provided for accurate maintenance of the equipment. However, at present, the state detection and routine maintenance of most systems are still biased to the diagnosis and maintenance of the faults which have occurred, and the early detection of the faults is still lack of applicable methods and technologies, so that in order to improve the efficiency, reduce the production and operation cost, ensure the operation safety, and urgently need to provide a scientific and feasible health assessment scheme.
On the other hand, with the continuous development of machine learning and AI technology in recent years, a rich framework and tools are provided for fault prediction and status maintenance, so that health management is possible, not just limited to concepts. Advanced AI technology combined with actual measurement is applied to health management and has become a mainstream development trend. A plurality of health assessment techniques are described in detail in Zhoulin, zhao Jie, feng Anfei, equipment failure prediction and health management techniques, published by national defense Industrial Press, but these methods do not make good use of artificial intelligence tools and often rely on excessive expert experience, which makes specific implementation hindered.
Disclosure of Invention
The invention aims to provide an equipment health assessment method, storage equipment and a terminal, which can obtain the health assessment state of equipment and provide support for realizing maintenance decision based on the state.
The first aspect of the present invention provides an equipment health assessment method, comprising the steps of:
s100, acquiring non-degradation parameters of sample equipment, wherein the non-degradation parameters comprise: index characteristic parameters and influence factor characteristic parameters of normal operation of sample equipment without performance degradation stage;
s200, generating a training sample according to the non-degradation parameters;
S300, training according to the training sample and obtaining a normal behavior model, wherein the normal behavior model comprises: the functional relation between index characteristic parameters and influence factor characteristic parameters of the sample equipment in the normal operation and performance degradation-free stage;
S400, obtaining the characteristic parameters of the actual measurement indexes and the characteristic parameters of the actual measurement influence factors of the equipment to be evaluated;
S500, inputting the characteristic parameters of the actually measured influencing factors into the normal behavior model and obtaining the characteristic parameters of expected indexes;
And S600, obtaining a health evaluation result of the equipment to be evaluated according to the expected index characteristic parameter and the actual measurement index characteristic parameter.
In one possible implementation, in step S200, the method specifically includes the following steps:
s210, performing slicing processing on the non-degradation parameters, and obtaining a plurality of slicing parameters;
s220, training samples are generated according to the plurality of slicing parameters.
In one possible implementation, in step S220, the method specifically includes the following steps:
S221, preprocessing the plurality of fragment parameters, wherein the preprocessing comprises the following steps: missing value processing or outlier processing;
S222, generating training samples according to the preprocessed plurality of slicing parameters.
In one possible implementation, in step S600, the method specifically includes the following steps:
S610, obtaining performance index parameters according to the expected index characteristic parameters and the actually measured index characteristic parameters;
S620, acquiring a limit value of a performance index parameter, and acquiring a degradation degree according to the performance index parameter and the limit value of the performance index parameter;
S630, determining the number of equipment health grade numbers, and acquiring a membership distribution function according to the number of equipment health grade numbers;
S640, obtaining membership vectors under the health grades of all equipment according to the degradation degree and the membership distribution function;
S650, acquiring the equipment health grade of the equipment to be evaluated according to the membership vector of each equipment health grade;
And S660, obtaining a health evaluation result of the equipment to be evaluated according to the equipment health grade of the equipment to be evaluated.
In one possible implementation, in step S610, the following formula is specifically used:
a performance index parameter deltay is obtained, wherein, And y is the actual measurement index characteristic parameter for the expected index characteristic parameter.
In one possible implementation, in step S620, the following formula is specifically used:
Or formula:
Or formula:
The degradation degree u is obtained by one of the formulas in (a),
Wherein deltay is the performance index parameter, delta is the limit value of the performance index parameter,
K is an adjustment coefficient and abs is an absolute function.
In one possible implementation, in step S640, the following formula is specifically used:
And obtaining a membership degree vector g i (u) which corresponds to the degree of degradation u and belongs to the health grade of each equipment, wherein i is the number of the health grade of the equipment, and [ a i,bi,ci ] is a preset value.
In one possible implementation, in step S650, the following formula is specifically used:
l＝{i|max(gi(u))}
The equipment grade l, i is the equipment health grade number, and g i (u) is the membership vector of each equipment health grade corresponding to the degradation degree u.
In one possible solution, step S600 is replaced by: sequentially repeating steps S100, S200, S300, S400, S500, S610, S620, S630 and S640 in multiple dimensions to obtain degradation degree and membership degree vectors of the equipment to be evaluated in each dimension;
And, after the completion of the repeating action, further comprising the steps of:
And S700, obtaining a health evaluation result of the equipment to be evaluated according to the degradation degree and the membership degree vector of the equipment to be evaluated in each dimension.
In one possible scheme, the step S700 specifically includes the following steps:
s710, obtaining a weight vector according to degradation degrees in multiple dimensions;
S720, constructing a fuzzy judgment matrix according to membership vectors in multiple dimensions;
S730, obtaining a comprehensive membership vector according to the weight vector and the fuzzy judgment matrix;
s740, acquiring the equipment health grade of the equipment to be evaluated according to the comprehensive membership vector;
s750, obtaining a health evaluation result of the equipment to be evaluated according to the equipment health grade of the equipment to be evaluated.
In one possible implementation, in step S710, the following formula is specifically used:
Obtaining a weight w i, wherein U i is the degradation degree of the ith dimension, and n is the number of dimensions;
And further according to the formula:
{W}1*n＝[w1,w2,…wn]
the weight vector { W } 1*n is obtained.
In one possible implementation, in step S730, the following formula is specifically used:
V＝WB
And obtaining a comprehensive membership vector V, wherein W is a weight vector, and B is a fuzzy judgment matrix.
In one possible implementation, in step S740, the following formula is specifically adopted:
V＝[v1,v2…vn]
the formula:
l＝{i|max(vi)}
The equipment level l is obtained and the equipment level,
Wherein the comprehensive membership vector V, V i is the membership vector of the ith dimension.
A second aspect of the present invention provides a storage device having stored therein a plurality of instructions adapted to be loaded by a processor and to perform the method of equipment health assessment as in any one of the possible scenarios referred to in the first aspect above.
A third aspect of the present invention provides a terminal, comprising:
A processor adapted to implement instructions; and
A storage device adapted to store a plurality of instructions, characterized in that the instructions are adapted to be loaded by a processor and to perform the method of equipment health assessment as in any one of the possible scenarios referred to in the first aspect above.
Compared with the prior art, the equipment health evaluation method, the storage device and the terminal provided by the invention can fully utilize the actually measured advanced AI technology to mine the equipment performance index, provide reliable data support for evaluating the equipment health grade, ensure the real-time performance of the performance index, ensure that the evaluation result is the evaluation of the actually measured real-time state, and not just the rough evaluation result obtained by the statistical rule, thereby providing a powerful basis for the overall performance evaluation and early fault early warning of the equipment. On the other hand, the training of the normal behavior model only needs data of a normal operation stage, and a large number of fault samples are not needed, so that the data is easier to acquire, and the whole flow is easier to realize.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it will be obvious that the drawings in the following description are some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flowchart of an equipment health assessment method according to a first embodiment of the present invention;
Fig. 2 is a flowchart of step S600 in the first 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 embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. 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 technical scheme of the invention is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
In a first embodiment, a method for implementing an equipment health assessment method is provided, where the method is equipment health assessment under a single index condition, as shown in fig. 1, and the specific steps are as follows:
s100, acquiring non-degradation parameters of sample equipment, wherein the non-degradation parameters comprise: index characteristic parameters and influence factor characteristic parameters of normal operation of sample equipment without performance degradation stage;
s200, generating a training sample according to the non-degradation parameters;
S300, training according to the training sample and obtaining a normal behavior model, wherein the normal behavior model comprises: the functional relation between index characteristic parameters and influence factor characteristic parameters of the sample equipment in the normal operation and performance degradation-free stage;
S400, obtaining the characteristic parameters of the actual measurement indexes and the characteristic parameters of the actual measurement influence factors of the equipment to be evaluated;
S500, inputting the characteristic parameters of the actually measured influencing factors into the normal behavior model and obtaining the characteristic parameters of expected indexes;
And S600, obtaining a health evaluation result of the equipment to be evaluated according to the expected index characteristic parameter and the actual measurement index characteristic parameter.
For example, the equipment health assessment method is used to assess the service life of the drive motor.
In step S100, a plurality of driving motors with the same model are used as sample equipment, and non-degradation parameters of the driving motors with the same model are collected, where the non-degradation parameters refer to parameters of normal operation and no performance degradation stage of the driving motors. Due to the large number of parameters during the operation of the device, for example: the current, voltage, rotation speed, temperature and the like can be used for determining index characteristic parameters and influence factor characteristic parameters in advance according to business logic and data exploration processes. For example, the index feature parameter is an operation mileage, the influencing factor feature parameter is a maximum rotation speed, and the non-degradation parameter includes the operation mileage and the maximum rotation speed.
Step S200 may be to convert the running mileage and the maximum rotation speed into training samples suitable for machine learning through a computer algorithm.
Step S300 may be to input the training samples into a machine learning model, and obtain a normal behavior model after machine training. Namely, in the normal operation stage of training, the relation y=f (x) between the index characteristic parameter and the influence factor characteristic parameter, wherein y is a scalar quantity, represents the index characteristic parameter, x is a vector, represents the influence factor characteristic parameter, f is a function learned by a machine learning model, and the corresponding relation between the normal operation stage x and y is described. The specific model can be selected from a linear model, a neural network model, a support vector regression model, a random forest and the like in the prior art.
Step S400 may be to test the driving motor to be evaluated, and obtain the measured running mileage and the maximum rotation speed, that is, the measured index feature parameter and the measured influencing factor feature parameter respectively.
Step S500 may be to input the measured maximum rotation speed into the normal behavior model and obtain the expected operation mileage.
In step S600, the measured running mileage is compared with the expected running mileage to obtain a health evaluation result of the driving motor to be evaluated, for example, the measured running mileage is less than the expected running mileage, the health evaluation result of the driving motor is "deteriorated", the measured running mileage is equal to the expected running mileage, the health evaluation result of the driving motor is "good", the measured running mileage is greater than the expected running mileage, and the health evaluation result of the driving motor is "healthy".
Through the above, it is easily found that the equipment health assessment method provided by the embodiment can fully utilize the actually measured advanced AI technology to mine the equipment performance index, provide reliable data support for assessing the equipment health grade, ensure that the assessment result is the assessment of the actually measured real-time state, and not just the rough assessment result obtained through the statistical rule, thereby providing a powerful basis for the overall performance assessment and early fault early warning of the equipment. On the other hand, the training of the normal behavior model only needs data of a normal operation stage, and a large number of fault samples are not needed, so that the data is easier to acquire, and the whole flow is easier to realize. And the degradation condition of the equipment is characterized by analyzing the deviation condition of the index characteristic parameters and the expected values of the index characteristic parameters when the equipment actually runs, so that the health grade of the equipment is evaluated, and support is provided for realizing maintenance decision based on states. The method can solve the problems of lack of an integral performance analysis and evaluation method and lack of early fault detection and early warning of most equipment monitoring systems at present, provide decision support for maintenance based on states, increase equipment safety and reduce unnecessary expenses.
Optionally, in step S200, the following steps are specifically included:
s210, performing slicing processing on the non-degradation parameters, and obtaining a plurality of slicing parameters;
s220, training samples are generated according to the plurality of slicing parameters.
The slicing rules can be determined according to business rules and optimized according to the exploration process. For example, the fragmentation effect on the data may be achieved by tagging the data in a database.
Further, in step S220, the method specifically includes the following steps:
S221, preprocessing the plurality of fragment parameters, wherein the preprocessing comprises the following steps: missing value processing or outlier processing;
S222, generating training samples according to the preprocessed plurality of slicing parameters.
After preprocessing the segmented data, the features of each segment can be extracted by using the preprocessed data to construct training samples, and each segment generates a training sample. The preprocessing method and the feature extraction scheme are determined by a data exploration process. The common preprocessing method can be the missing value processing and the outlier processing in the prior art. Missing values are typically discarded or filled in using linear interpolation or cubic spline interpolation, and outliers are removed by the box plot method. The feature extraction method can be determined according to research targets and business logic, and common features include average values or extremum values and the like.
Optionally, as shown in fig. 2, in step S600, the following steps are specifically included:
S610, obtaining performance index parameters according to the expected index characteristic parameters and the actually measured index characteristic parameters;
S620, acquiring a limit value of a performance index parameter, and acquiring a degradation degree according to the performance index parameter and the limit value of the performance index parameter;
S630, determining the number of equipment health grade numbers, and acquiring a membership distribution function according to the number of equipment health grade numbers;
S640, obtaining membership vectors under the health grades of all equipment according to the degradation degree and the membership distribution function;
S650, acquiring the equipment health grade of the equipment to be evaluated according to the membership vector of each equipment health grade;
And S660, obtaining a health evaluation result of the equipment to be evaluated according to the equipment health grade of the equipment to be evaluated.
Optionally, in step S610, specifically, according to the formula:
a performance index parameter deltay is obtained, wherein, And y is the actual measurement index characteristic parameter for the expected index characteristic parameter.
Optionally, in step S620, specifically, according to formula one:
or formula two:
Or formula three:
The degradation degree u is obtained by one of the formulas in (a),
Wherein deltay is the performance index parameter, delta is the limit value of the performance index parameter,
K is an adjustment coefficient, k is typically 1 or 2, abs is an absolute function.
It should be noted that, the limit value δ of the performance index parameter may be provided by a service expert or a data expert, the degradation degree is defined by a formula one for the larger and more optimal index y, the degradation degree is defined by a formula two for the smaller and more optimal index y, and the degradation degree is defined by a formula three for the optimal index y within a certain range.
For convenience of explanation, the equipment health grade is classified into five grades "a", "B", "C", "D", "E", and respectively represents five states of "health", "good", "attention", "worsening", "disease". A suitable health status membership distribution function g i is selected,
I=1, 2,3,4,5. Substituting the degree of degradation into the membership distribution function to obtain a membership vector [ g 1(u),g2(u),g3(u),g4(u),g5 (u) ] of each grade to which the degree of degradation corresponds, wherein g i (u) represents the degree of membership of the degree of degradation to the ith grade, i=1 represents health, and so on. The most commonly used membership functions are triangular membership functions or ridge-shaped distribution membership functions.
Optionally, in step S640, a triangle membership function is selected, specifically according to the formula:
Obtaining a membership degree vector g i (u) belonging to each equipment health grade corresponding to the degradation degree u, wherein i is the number of equipment health grades, [ a i,bi,ci ] is a preset value, for example, [ a i,bi,ci ], and [0,0,0.3], [0,0.3,0.5], [0.3,0.5,0.7], [0.5,0.7,1], [0.7,1,1] are respectively taken for i=1, 2,3,4, 5.
Optionally, in step S650, specifically according to the formula:
l＝{i|max(gi(u))}
The equipment grade l, i is the equipment health grade number, and g i (u) is the membership vector of each equipment health grade corresponding to the degradation degree u.
I.e. according to the principle of maximum membership, which state the drive motor belongs to in "healthy", "good", "attention", "worsening", "disease" is determined according to l.
The second embodiment is an alternative of the first embodiment, and the second embodiment provides a method for implementing the equipment health assessment method, where the method is equipment health assessment under the multi-index condition, and the difference between the second embodiment and the first embodiment is that the step S600 in the first embodiment is replaced by: steps S100, S200, S300, S400, S500, S610, S620, S630 and S640 in the first embodiment are sequentially repeated in multiple dimensions to obtain degradation degrees and membership degree vectors of the equipment to be evaluated in each dimension;
And, after the completion of the repeating action, further comprising the steps of:
And S700, obtaining a health evaluation result of the equipment to be evaluated according to the degradation degree and the membership degree vector of the equipment to be evaluated in each dimension.
Optionally, in step S700, the method specifically includes the following steps:
s710, obtaining a weight vector according to degradation degrees in multiple dimensions;
S720, constructing a fuzzy judgment matrix according to membership vectors in multiple dimensions;
S730, obtaining a comprehensive membership vector according to the weight vector and the fuzzy judgment matrix;
s740, acquiring the equipment health grade of the equipment to be evaluated according to the comprehensive membership vector;
s750, obtaining a health evaluation result of the equipment to be evaluated according to the equipment health grade of the equipment to be evaluated.
For example, the multidimensional index characteristic parameter is the running mileage and the current, the influencing factor characteristic parameter is the maximum rotation speed and the voltage, and the non-degradation parameter comprises the running mileage, the current, the maximum rotation speed and the voltage.
The degradation degree in the multiple dimensions is the degradation degree of the maximum rotation speed and the degradation degree of the voltage, and the membership degree vector in the multiple dimensions is the membership degree vector of the maximum rotation speed and the membership degree vector of the voltage.
Through the above, the invention can fully utilize the current advanced AI technology to mine the performance index of the equipment, provide reliable data support for evaluating the health grade of the equipment, ensure that the evaluation result is the evaluation of the current real-time state, and not just the rough evaluation result obtained by the statistical rule, thereby providing a powerful basis for the overall performance evaluation and early fault early warning of the equipment. In addition, the synthesis technology of the multi-index health grade avoids the requirement of providing weight vectors by an expert, and increases the operability of the evaluation process.
Optionally, in step S710, specifically according to the formula:
Obtaining a weight w i, wherein U i is the degradation degree of the ith dimension, and n is the number of dimensions;
And further according to the formula:
{W}1*n＝[w1,w2,…wn]
The weight vector { W } 1*n is obtained. When λ i is infinite, i.e. u i =1, then the corresponding The balance being 0, m being the number of dimensions with a degree of degradation of 1.
Optionally, in step S730, specifically, according to the formula:
V＝WB
And obtaining a comprehensive membership vector V, wherein W is a weight vector, and B is a fuzzy judgment matrix. For example, a fuzzy evaluation matrix { B } n*5＝[B1,B2…Bn]T is formed by membership vectors.
Optionally, in step S740, specifically, according to the formula:
V＝[v1,v2…vn]
the formula:
l＝{i|max(vi)}
The equipment level l is obtained and the equipment level,
Wherein the comprehensive membership vector V, V i is the membership vector of the ith dimension.
Namely, according to the principle of maximum membership, the health state of the driving motor can be determined according to l.
In a second embodiment, a storage device is provided, in which a plurality of instructions are stored, the instructions being adapted to be loaded by a processor and to perform the equipment health assessment method according to the first or second embodiments described above.
In a third embodiment, a terminal is provided, including:
A processor adapted to implement instructions; and
A storage device adapted to store a plurality of instructions, wherein the instructions are adapted to be loaded by a processor and to perform the method of assessing equipment health as referred to in the first or second embodiments above.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (7)
1. A method of equipment health assessment, comprising the steps of:
s100, acquiring non-degradation parameters of sample equipment, wherein the non-degradation parameters comprise: index characteristic parameters and influence factor characteristic parameters of normal operation of sample equipment without performance degradation stage;
S200, generating a training sample according to the non-degradation parameters; the method specifically comprises the following steps:
s210, performing slicing processing on the non-degradation parameters, and obtaining a plurality of slicing parameters;
s220, generating training samples according to the plurality of slicing parameters;
S300, training according to the training sample and obtaining a normal behavior model, wherein the normal behavior model comprises: the functional relation between index characteristic parameters and influence factor characteristic parameters of the sample equipment in the normal operation and performance degradation-free stage;
S400, obtaining the characteristic parameters of the actual measurement indexes and the characteristic parameters of the actual measurement influence factors of the equipment to be evaluated;
S500, inputting the characteristic parameters of the actually measured influencing factors into the normal behavior model and obtaining the characteristic parameters of expected indexes;
S600, obtaining a health evaluation result of the equipment to be evaluated according to the expected index characteristic parameter and the actual measurement index characteristic parameter;
in step S600, the method specifically includes the following steps:
S610, obtaining performance index parameters according to the expected index characteristic parameters and the actually measured index characteristic parameters;
S620, acquiring a limit value of a performance index parameter, and acquiring a degradation degree according to the performance index parameter and the limit value of the performance index parameter;
S630, determining the number of equipment health grade numbers, and acquiring a membership distribution function according to the number of equipment health grade numbers;
S640, obtaining membership vectors under the health grades of all equipment according to the degradation degree and the membership distribution function;
S650, acquiring the equipment health grade of the equipment to be evaluated according to the membership vector of each equipment health grade;
s660, obtaining a health evaluation result of the equipment to be evaluated according to the equipment health grade of the equipment to be evaluated;
in step S610, specifically, according to the formula:
，
a performance index parameter deltay is obtained, wherein, The characteristic parameters of the expected indexes are shown in the specification, and y is the characteristic parameters of the actual measured indexes;
in step S620, specifically, according to the formula:
，
Or formula:
，
Or formula:
The degradation degree u is obtained by one formula in (1), wherein deltay is a performance index parameter, delta is a limit value of the performance index parameter,
K is an adjustment coefficient, abs is an absolute function;
In step S640, specifically, according to the formula:
，
Obtaining a membership vector gi (u) corresponding to the degree of degradation u and belonging to each equipment health grade, wherein i is equipment health
The number of levels, [ ai, bi, ci ] is a preset value;
In step S650, specifically, according to the formula:
l＝{i|max(gi(u))}
obtaining equipment grades l, i are equipment health grade numbers, and gi (u) is a membership vector corresponding to the degradation degree u and belonging to each equipment health grade;
Sequentially repeating steps S100, S200, S300, S400, S500, S610, S620, S630 and S640 in multiple dimensions to obtain degradation degree and membership degree vectors of the equipment to be evaluated in each dimension;
And, after the completion of the repeating action, further comprising the steps of:
s700, obtaining a health evaluation result of the equipment to be evaluated according to the degradation degree and the membership degree vector of the equipment to be evaluated in each dimension; the method specifically comprises the following steps:
s710, obtaining a weight vector according to degradation degrees in multiple dimensions;
S720, constructing a fuzzy judgment matrix according to membership vectors in multiple dimensions;
S730, obtaining a comprehensive membership vector according to the weight vector and the fuzzy judgment matrix;
s740, acquiring the equipment health grade of the equipment to be evaluated according to the comprehensive membership vector;
s750, obtaining a health evaluation result of the equipment to be evaluated according to the equipment health grade of the equipment to be evaluated.
2. The equipment health assessment method according to claim 1, characterized in that in step S220, specifically comprising the steps of:
S221, preprocessing the plurality of fragment parameters, wherein the preprocessing comprises the following steps: missing value processing or outlier processing;
S222, generating training samples according to the preprocessed plurality of slicing parameters.
3. The equipment health assessment method according to claim 1, characterized in that in step S710, it is specifically according to the formula:
，
Obtain a weight wi, wherein Ui is the degradation degree of the ith dimension, n is the number of dimensions;
And further according to the formula:
{W}1*n＝[w1,w2,…wn]
the weight vector { W }1*n is obtained.
4. The equipment health assessment method according to claim 1, characterized in that in step S730, it is specifically according to the formula:
V＝WB，
And obtaining a comprehensive membership vector V, wherein W is a weight vector, and B is a fuzzy judgment matrix.
5. The equipment health assessment method according to claim 1, characterized in that in step S740, it is specifically according to the formula:
V＝[v1,v2…vn]
the formula:
l＝{i|max(vi)}
The equipment level l is obtained and the equipment level,
Wherein, the comprehensive membership vector V, vi is the membership vector of the ith dimension.
6. A storage device storing a plurality of instructions adapted to be loaded by a processor and to perform the method of equipment health assessment of claim 1.
7. A terminal, comprising:
A processor adapted to implement instructions; and
A storage device adapted to store a plurality of instructions, wherein the instructions are adapted to be loaded by a processor and to perform the equipment health assessment method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910850541.6A CN112488432B (en) | 2019-09-10 | 2019-09-10 | Equipment health assessment method, storage device and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910850541.6A CN112488432B (en) | 2019-09-10 | 2019-09-10 | Equipment health assessment method, storage device and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112488432A CN112488432A (en) | 2021-03-12 |
| CN112488432B true CN112488432B (en) | 2024-05-07 |
Family
ID=74920152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910850541.6A Active CN112488432B (en) | 2019-09-10 | 2019-09-10 | Equipment health assessment method, storage device and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112488432B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700321A (en) * | 2015-03-16 | 2015-06-10 | 国家电网公司 | Analytical method of state running tendency of transmission and distribution equipment |
| CN105488344A (en) * | 2015-11-26 | 2016-04-13 | 中国电力科学研究院 | Universal evaluation method for health index of power distribution equipment |
| CN105512962A (en) * | 2016-01-13 | 2016-04-20 | 武汉大学 | Method for comprehensively evaluating insulation status of gas insulated switchgear (GIS) |
| CN105716857A (en) * | 2016-01-20 | 2016-06-29 | 中国人民解放军军械工程学院 | Planetary gearbox health state assessment method |
| CN106199305A (en) * | 2016-07-01 | 2016-12-07 | 太原理工大学 | Underground coal mine electric power system dry-type transformer insulation health state evaluation method |
| CN107016235A (en) * | 2017-03-21 | 2017-08-04 | 西安交通大学 | The equipment running status health degree appraisal procedure adaptively merged based on multiple features |
| CN108470246A (en) * | 2018-03-14 | 2018-08-31 | 广东电网有限责任公司电网规划研究中心 | A kind of planning distribution network reliability index evaluating method of feature based parameter |
| CN108874733A (en) * | 2018-04-25 | 2018-11-23 | 明阳智慧能源集团股份公司 | A kind of large-scale half direct-drive unit health state evaluation method |
| CN109685366A (en) * | 2018-12-24 | 2019-04-26 | 中国人民解放军32181部队 | Equipment health state evaluation method based on mutation data |
| CN109886430A (en) * | 2019-01-24 | 2019-06-14 | 同济大学 | A kind of equipment health state evaluation and prediction technique based on industrial big data |
| CN109934358A (en) * | 2019-01-30 | 2019-06-25 | 中国人民解放军32181部队 | Equipment failure prediction and health evaluating method, system and terminal device |
-
2019
- 2019-09-10 CN CN201910850541.6A patent/CN112488432B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700321A (en) * | 2015-03-16 | 2015-06-10 | 国家电网公司 | Analytical method of state running tendency of transmission and distribution equipment |
| CN105488344A (en) * | 2015-11-26 | 2016-04-13 | 中国电力科学研究院 | Universal evaluation method for health index of power distribution equipment |
| CN105512962A (en) * | 2016-01-13 | 2016-04-20 | 武汉大学 | Method for comprehensively evaluating insulation status of gas insulated switchgear (GIS) |
| CN105716857A (en) * | 2016-01-20 | 2016-06-29 | 中国人民解放军军械工程学院 | Planetary gearbox health state assessment method |
| CN106199305A (en) * | 2016-07-01 | 2016-12-07 | 太原理工大学 | Underground coal mine electric power system dry-type transformer insulation health state evaluation method |
| CN107016235A (en) * | 2017-03-21 | 2017-08-04 | 西安交通大学 | The equipment running status health degree appraisal procedure adaptively merged based on multiple features |
| CN108470246A (en) * | 2018-03-14 | 2018-08-31 | 广东电网有限责任公司电网规划研究中心 | A kind of planning distribution network reliability index evaluating method of feature based parameter |
| CN108874733A (en) * | 2018-04-25 | 2018-11-23 | 明阳智慧能源集团股份公司 | A kind of large-scale half direct-drive unit health state evaluation method |
| CN109685366A (en) * | 2018-12-24 | 2019-04-26 | 中国人民解放军32181部队 | Equipment health state evaluation method based on mutation data |
| CN109886430A (en) * | 2019-01-24 | 2019-06-14 | 同济大学 | A kind of equipment health state evaluation and prediction technique based on industrial big data |
| CN109934358A (en) * | 2019-01-30 | 2019-06-25 | 中国人民解放军32181部队 | Equipment failure prediction and health evaluating method, system and terminal device |
Non-Patent Citations (1)
| 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;20180828(第08期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112488432A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102022201761A1 (en) | Method, system and storage medium for automatically diagnosing devices | |
| CN111178553A (en) | Industrial equipment health trend analysis method and system based on ARIMA and LSTM algorithms | |
| US7464063B2 (en) | Information processor, state judging unit and diagnostic unit, information processing method, state judging method and diagnosing method | |
| CN110414154B (en) | Fan component temperature abnormity detection and alarm method with double measuring points | |
| CN112200327B (en) | MES equipment maintenance early warning method and system | |
| CN114813105A (en) | Gear box fault early warning method and system based on working condition similarity evaluation | |
| CN111337244B (en) | Method and device for monitoring and diagnosing faults of input shaft of fan gearbox | |
| Mosallam et al. | Component based data-driven prognostics for complex systems: Methodology and applications | |
| CN114462259B (en) | SOC-based battery remaining life prediction method and system, automobile and medium | |
| CN114444582A (en) | Mechanical equipment fault diagnosis method based on convolutional neural network and Bayesian network | |
| CN107122907B (en) | Method for analyzing symbolized quality characteristics of mechanical and electrical products and tracing fault reasons | |
| CN116561514A (en) | Method, system, device and medium for diagnosing faults of vehicle hub bearing unit | |
| CN113424119A (en) | Work efficiency evaluation method, work efficiency evaluation device, and program | |
| CN114036647A (en) | Power battery safety risk assessment method based on real vehicle data | |
| CN113987027A (en) | Equipment state determination method, device and medium based on fault prediction | |
| CN112488432B (en) | Equipment health assessment method, storage device and terminal | |
| CN117034001A (en) | Wind turbine generator system fault prediction method and device and electronic equipment | |
| CN116914917A (en) | Big data-based monitoring and management system for operation state of power distribution cabinet | |
| CN116705272A (en) | Comprehensive evaluation method for equipment health state based on multidimensional diagnosis | |
| CN116928038A (en) | Fault early warning method and device based on main bearing temperature of offshore wind turbine generator | |
| CN116702597A (en) | Mechanical equipment operation life prediction and health management method, system and medium | |
| CN116625686A (en) | On-line diagnosis method for bearing faults of aero-engine | |
| CN115326393A (en) | Wind turbine generator bearing pair fault diagnosis method based on temperature information | |
| CN114036035A (en) | Method for recognizing abnormity based on real-time data traffic complexity | |
| KR20230075150A (en) | Method for managing system health |
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 |