CN112416928B - Demand prediction model for first-aid repair spare parts of ground complex electronic equipment - Google Patents
Demand prediction model for first-aid repair spare parts of ground complex electronic equipment Download PDFInfo
- Publication number
- CN112416928B CN112416928B CN202011283043.7A CN202011283043A CN112416928B CN 112416928 B CN112416928 B CN 112416928B CN 202011283043 A CN202011283043 A CN 202011283043A CN 112416928 B CN112416928 B CN 112416928B
- Authority
- CN
- China
- Prior art keywords
- data
- damage
- training
- equipment
- electronic equipment
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2291—User-Defined Types; Storage management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of methods for predicting the requirement of a specific equipment first-aid repair spare part, in particular to a model for predicting the requirement of a ground complex electronic equipment first-aid repair spare part, which comprises the following steps: 1. constructing a ground complex electronic equipment damage database; 2. training a prediction machine based on equipment damage data; 3. and predicting the need of first-aid repair spare parts. The equipment damage data are trained through machine learning, the occurrence rule of equipment damage can be extracted, the damage condition of specific equipment can be predicted by means of the rule, and therefore the requirement for rush-repair of spare parts is met.
Description
Technical Field
The invention relates to the field of methods for predicting the requirement of a spare part for first-aid repair of specific equipment, in particular to a model for predicting the requirement of the spare part for first-aid repair of ground complex electronic equipment.
Background
The first-aid repair spare parts are important material foundations for implementing battlefield first-aid repair of ground complex electronic equipment and are important factors for improving equipment regeneration capacity and maintaining fighting capacity in wartime. Whether spare parts can be effectively provided in time directly relates to whether battlefield first-aid repair work can be smoothly carried out, and further influences the readiness rate of equipment. The problem is the precise guarantee problem of the requirement of the emergency repair spare parts. Whether computer simulation, actual installation experimental data or actual combat data indicate that the damaged parts and components of the equipment have certain regularity. Therefore, the invention provides a demand prediction model of a complex ground electronic equipment first-aid repair spare part based on equipment damage data, and provides a construction method and a learning and training process of an equipment damage database.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a demand prediction model for a complex ground electronic equipment first-aid repair spare part.
The technical scheme adopted by the invention for solving the technical problems is as follows: the demand prediction model for the emergency repair spare parts of the ground complex electronic equipment comprises the following steps:
(1) Ground complex electronic equipment damage database construction
In a ground complex electronic equipment damage table, selecting a 'warehousing number' as a main key of the table, wherein the table cannot be empty, and determining other attributes according to damage data acquisition conditions;
(2) Predictive engine training based on equipment damage data
The intelligent training of ground complex electronic equipment damage is carried out by utilizing a machine learning algorithm, and the process is as follows:
1) Under the condition of given training parameters, generating a prediction machine through training of training data;
2) Inputting the data to be targeted into a prediction machine, and outputting a prediction result;
3) According to the prediction result, whether new data is added into the training sample library or not is considered;
4) Training sample data in the training process is taken from a ground complex electronic equipment damage database, and in a ground complex electronic equipment damage data table and a damage grade table, according to a public keyword 'damage grade', the correlation between a damage value and ground complex electronic equipment damage data is established, and a prediction model learning training sample table is generated;
5) In a training sample table of a prediction machine, training sample data mainly comprises equipment subsystem damage data and equipment damage values, wherein each subsystem damage data comprises subsystem and functional unit damage data;
6) The data pattern of the training sample table generated thereby in the database, wherein the 'data source' and the 'training mark' are used as selection conditions for the data to participate in training learning;
7) In the training sample table, the subsystem damage data of each group of data are not necessarily involved in training, but the damage data in the training sample table are correspondingly combined according to the selection requirement of the actual subsystem to form training data;
(3) First-aid repair spare part demand prediction
According to the generated prediction machine, a prediction model is built, and the demand prediction of the first-aid repair spare parts of the ground complex electronic equipment is carried out:
a. model module
The input module comprises an equipment combat damage database, an equipment standardized structure, an equipment damage mode and equipment combat damage data;
the output module comprises spare part requirements;
b. model work mechanism
Firstly, learning and training by using an equipment combat damage database to generate a spare part demand prediction model;
inputting equipment combat damage data of specific models into a prediction model;
finally, outputting the requirement condition of the equipment spare parts;
c. model function
After the equipment battlefield damage spare part prediction model is built, the requirement condition of each spare part of equipment can be output through the prediction model for the specific equipment damage prior data, and the requirement condition of each spare part of equipment can be output through the prediction model for the equipment damage prior data which is not provided.
Preferably, when the record is added to the training sample, all attribute values are required to be null, and the data types of the attributes in the damage table are different, mainly because the dimension and the numerical length of each damage data are not all the same.
Preferably, the training flag is "Y" to indicate that the group of data participates in training learning, and if the training flag is "N" to indicate that the group of data does not participate in training learning, the training flag is only used as data accumulation.
The invention has the beneficial effects that:
according to the demand prediction model for the emergency repair spare parts of the complex ground electronic equipment, disclosed by the invention, a large amount of equipment damage data are trained through machine learning, so that the occurrence rule of equipment damage can be extracted, and the damage condition of specific equipment can be predicted by means of the rule, so that the demand of the emergency repair spare parts is obtained.
Drawings
The invention is further illustrated with reference to the following figures and examples.
FIG. 1 is a flow chart of a demand prediction model for a first-aid repair spare part of a ground complex electronic equipment provided by the invention;
FIG. 2 is a schematic diagram of data records of a ground complex electronic equipment damage library in a ground complex electronic equipment first-aid repair spare part demand prediction model provided by the invention;
FIG. 3 is a flow chart of a training process of a prediction machine in a demand prediction model of a complex ground electronic equipment emergency repair spare part provided by the invention;
FIG. 4 is a prediction model learning training sample table in a demand prediction model of a complex ground electronic equipment emergency repair spare part provided by the invention;
FIG. 5 is a data pattern diagram of a training sample in a database in a demand prediction model of a ground complex electronic equipment emergency repair spare part provided by the invention;
FIG. 6 is a graph generated by training data in a demand prediction model for a complex ground electronic equipment emergency repair spare part provided by the invention;
FIG. 7 is a diagram of a demand model of emergency repair spare parts in a demand prediction model of a complex ground electronic equipment emergency repair spare part provided by the invention;
fig. 8 is a data format of a training sample in a demand prediction model for a ground complex electronic equipment emergency repair spare part provided by the invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.
As shown in fig. 1 to 8, the model for predicting the demand of the first-aid repair spare part of the ground complex electronic equipment comprises the following steps:
(1) Ground complex electronic equipment damage database construction
In the ground complex electronic equipment damage table, a 'warehousing number' is selected as a main key of the table and cannot be empty, and other attributes are determined according to the damage data acquisition condition. But when the record is added to the training sample, all attribute values are required to be not null. The data types of attributes in the impairment tables vary, mainly because the dimensionality and numerical length of each impairment data is not all the same.
The equipment damage conditions obtained by each computer simulation, actual assembly experiment or actual combat data are different, so that the same ground complex electronic equipment is associated with a plurality of damage data records, the data record structure is shown in figure 2, and the damage number is the unique identifier of the ground complex electronic equipment damage table.
(2) Predictive engine training based on equipment damage data
Utilize machine learning algorithm to carry out the intelligent training of ground complicated electronic equipment damage, its process is: 1) Under the condition of given training parameters, generating a prediction machine through training of training data; 2) Inputting the data to be targeted into a prediction machine, and outputting a prediction result; 3) And according to the prediction result, whether new data is added into the training sample library or not is considered. This process is illustrated in fig. 3.
Training sample data in the training process is obtained from a ground complex electronic equipment damage database. In the ground complex electronic equipment damage data table and the damage level table, according to the common keyword "damage level", the association between the damage value and the ground complex electronic equipment damage data is established, and a prediction model learning training sample table is generated, as shown in fig. 4.
In the training sample table of the prediction machine, training sample data mainly comprises equipment subsystem damage data and equipment damage values, each subsystem damage data comprises subsystem and functional unit damage data, and the data format is shown in fig. 8.
The data pattern of the training sample table generated in this way in the database is shown in fig. 5, where "data source" and "training flag" are used as selection conditions for data to participate in training learning, where a training flag "Y" indicates that the group of data participates in training learning, and if the training flag "N" indicates that the group of data does not participate in training learning, the data pattern is used only as data accumulation.
In the training sample table, the subsystem damage data of each group of data does not necessarily participate in training, but the damage data in the training sample table is correspondingly combined according to the actual subsystem selection requirement to form training data, as shown in fig. 6.
(3) Demand forecast for first-aid repair spare parts
And constructing a prediction model according to the generated prediction machine, and predicting the requirement of the first-aid repair spare parts of the complex electronic equipment on the ground.
a. Model module
The input module comprises an equipment combat damage database, an equipment standardized structure, an equipment damage mode and equipment combat damage data;
the output module includes spare part requirements.
b. Model work mechanism
Firstly, learning and training by using an equipment combat damage database to generate a spare part demand prediction model; inputting equipment damage data of specific models into a prediction model; finally, the requirement condition of the equipment spare part is output, as shown in fig. 7.
c. Model function
After the equipment battlefield damage spare part prediction model is built, the requirement condition of each spare part of equipment can be output through the prediction model for the specific equipment damage prior data, and the requirement condition of each spare part of equipment can be output through the prediction model for the equipment damage prior data which is not provided.
The foregoing shows and describes the general principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and the embodiments and descriptions given above are only illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which fall within the scope of the claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (4)
1. The demand prediction model for the emergency repair spare parts of the ground complex electronic equipment is characterized by comprising the following steps of:
(1) Construction of ground complex electronic equipment damage database
In a ground complex electronic equipment damage table, selecting a 'warehousing number' as a main key of the table, wherein the 'warehousing number' cannot be empty, and other attributes are determined according to damage data acquisition conditions;
(2) Predictive engine training based on equipment damage data
Utilize machine learning algorithm to carry out the intelligent training of ground complicated electronic equipment damage, its process is:
1) Under the condition of given training parameters, generating a prediction machine through training of training data;
2) Inputting the data to be targeted into a prediction machine, and outputting a prediction result;
3) According to the prediction result, whether new data is added into the training sample library or not is considered;
4) Training sample data in the training process is taken from a ground complex electronic equipment damage database, and in a ground complex electronic equipment damage data table and a damage grade table, according to a public keyword 'damage grade', the correlation between a damage value and ground complex electronic equipment damage data is established, and a prediction model learning training sample table is generated;
5) In a training sample table of a prediction machine, training sample data mainly comprises equipment subsystem damage data and equipment damage values, wherein each subsystem damage data comprises subsystem and functional unit damage data;
6) The data pattern of the training sample table generated thereby in the database, wherein the 'data source' and the 'training mark' are used as selection conditions for the data to participate in training learning;
7) In the training sample table, the subsystem damage data of each group of data are not necessarily involved in training, but the damage data in the training sample table are correspondingly combined according to the selection requirement of the actual subsystem to form training data;
(3) Demand forecast for first-aid repair spare parts
According to the generated prediction machine, a prediction model is built, and the demand prediction of the first-aid repair spare parts of the ground complex electronic equipment is carried out:
a. model module
The input module comprises an equipment combat damage database, an equipment standardized structure, an equipment damage mode and equipment combat damage data;
the output module comprises spare part requirements;
b. model work mechanism
Firstly, learning and training by using an equipment combat damage database to generate a spare part demand prediction model;
inputting equipment combat damage data of specific models into a prediction model;
finally, outputting the requirement condition of the equipment spare parts;
c. model function
After a battlefield damage spare part prediction model is built, the demand condition of each spare part of the equipment is output through the prediction model.
2. The model for predicting the demand of first-aid repair spare parts of complex electronic equipment on the ground as claimed in claim 1 is characterized in that when the records are added into the training sample, all attribute values are required to be not null, and the data types of attributes in the damage table are different, mainly because the dimension and the numerical length of each damage data are not all the same.
3. The model for predicting the demand of first-aid repair spare parts of complex electronic equipment on the ground as claimed in claim 1, wherein the training flag is "Y" to indicate that the group of data participates in training and learning, and if the training flag is "N" to indicate that the group of data does not participate in training and learning, the training flag is only used as data accumulation.
4. The ground complex electronic equipment first-aid repair spare part demand prediction model of claim 1, characterized in that for the specific equipment damage prior data, the spare part demand condition of the equipment can be output through the prediction model, and for the equipment damage prior data which is not provided, the equipment damage database can be matched first.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011283043.7A CN112416928B (en) | 2020-11-16 | 2020-11-16 | Demand prediction model for first-aid repair spare parts of ground complex electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011283043.7A CN112416928B (en) | 2020-11-16 | 2020-11-16 | Demand prediction model for first-aid repair spare parts of ground complex electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112416928A CN112416928A (en) | 2021-02-26 |
| CN112416928B true CN112416928B (en) | 2022-10-04 |
Family
ID=74831353
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011283043.7A Active CN112416928B (en) | 2020-11-16 | 2020-11-16 | Demand prediction model for first-aid repair spare parts of ground complex electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112416928B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107958265A (en) * | 2017-11-21 | 2018-04-24 | 中国人民解放军陆军装甲兵学院 | Spare part Forecasting Methodology is damaged in a kind of war based on wartime influence factor and ε-SVR |
| CN111695692A (en) * | 2019-03-12 | 2020-09-22 | 现代自动车株式会社 | Apparatus and method for predicting damage degree |
-
2020
- 2020-11-16 CN CN202011283043.7A patent/CN112416928B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107958265A (en) * | 2017-11-21 | 2018-04-24 | 中国人民解放军陆军装甲兵学院 | Spare part Forecasting Methodology is damaged in a kind of war based on wartime influence factor and ε-SVR |
| CN111695692A (en) * | 2019-03-12 | 2020-09-22 | 现代自动车株式会社 | Apparatus and method for predicting damage degree |
Non-Patent Citations (1)
| Title |
|---|
| 飞机战伤抢修备件需求预测方法研究;蔡开龙等;《电光与控制》;20101201(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112416928A (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112613038B (en) | Knowledge graph-based security vulnerability analysis method | |
| CN110727804A (en) | Method and device for processing maintenance case by using knowledge graph and electronic equipment | |
| CN107016501A (en) | A kind of efficient industrial big data multidimensional analysis method | |
| CN109471929B (en) | Method for semantic search of equipment maintenance records based on map matching | |
| CN101894058B (en) | Method and device for analyzing test coverage automatically aiming at automatic test system | |
| CN109614669B (en) | Network-level bridge structure performance evaluation and prediction method | |
| CN111078094B (en) | Distributed machine learning visualization device | |
| KR20230104096A (en) | System and Method for providing early warning to prevent false alarm | |
| CN114918581B (en) | Welding parameter processing method and device, storage medium and processor | |
| Kamran et al. | Decision support system for the prediction of mine fire levels in underground coal mining using machine learning approaches | |
| CN114609994A (en) | Fault diagnosis method and device based on multi-granularity regularization rebalance incremental learning | |
| CN113219341A (en) | Model generation and battery degradation estimation device, method, medium, and apparatus | |
| CN103365923A (en) | Method and device for assessing partition schemes of database | |
| CN112416928B (en) | Demand prediction model for first-aid repair spare parts of ground complex electronic equipment | |
| Salim et al. | Classification predictive maintenance using XGboost with genetic algorithm | |
| CN112818003B (en) | Execution risk estimation method and device for query task | |
| CN110049108A (en) | A kind of net connection vehicular events generation method and device | |
| CN112214602A (en) | Text classification method and device based on humor, electronic equipment and storage medium | |
| KR102480518B1 (en) | Method for credit evaluation model update or replacement and apparatus performing the method | |
| Jing et al. | A microservice fault identification method based on LightGBM | |
| Yu et al. | A combinatorial clustering method for sequential fraud detection | |
| CN110543690B (en) | Parameter changing method for digital prototype of complex product model | |
| US20230237225A1 (en) | Machine learning based reservoir modeling | |
| CN115356949B (en) | Digital twin model consistency maintaining system and method | |
| Yang et al. | Research On Simulation Trade-off Analysis Method Of Reliability Index of Component-based Software |
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 |