CN113127538A - High-precision spare part demand prediction method - Google Patents
High-precision spare part demand prediction method Download PDFInfo
- Publication number
- CN113127538A CN113127538A CN202110411100.3A CN202110411100A CN113127538A CN 113127538 A CN113127538 A CN 113127538A CN 202110411100 A CN202110411100 A CN 202110411100A CN 113127538 A CN113127538 A CN 113127538A
- Authority
- CN
- China
- Prior art keywords
- spare parts
- metadata
- data
- spare part
- demand
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000012545 processing Methods 0.000 claims abstract description 29
- 238000010801 machine learning Methods 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 230000004927 fusion Effects 0.000 claims abstract description 16
- 238000012417 linear regression Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 238000005065 mining Methods 0.000 claims abstract description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 20
- 238000012423 maintenance Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 14
- 238000004519 manufacturing process Methods 0.000 claims description 11
- 230000008439 repair process Effects 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000007726 management method Methods 0.000 claims description 9
- 238000013277 forecasting method Methods 0.000 claims description 7
- 230000010354 integration Effects 0.000 claims description 7
- 238000013480 data collection Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 230000002776 aggregation Effects 0.000 claims description 5
- 238000004220 aggregation Methods 0.000 claims description 5
- 238000012550 audit Methods 0.000 claims description 4
- 230000008676 import Effects 0.000 claims description 3
- 238000012552 review Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000008901 benefit Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 239000000243 solution Substances 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000013439 planning Methods 0.000 description 3
- 230000002860 competitive effect Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000012086 standard solution Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
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
- G06F16/24—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
- 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
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q10/0875—Itemisation or classification of parts, supplies or services, e.g. bill of materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a high-precision spare part demand prediction method. The method comprises the following steps: collecting metadata related to spare part demand prediction, and storing the metadata after ETL processing into a database; preprocessing metadata stored in a database, performing data characteristic mining on the preprocessed metadata, determining each factor influencing the requirement of the spare part, analyzing the influence degree of each factor on the requirement of the spare part, inputting the source data into a machine learning fusion modeling prediction method based on Linear regression, AdaBoost and GBDT by using the metadata subjected to influence degree analysis processing, each useful influence factor and the influence degree of each sequenced influence factor on the requirement of the spare part as source data in the forecast stage of the requirement of the spare part, performing prediction analysis on the requirement quantity of the spare part in a certain month in the future, and outputting a prediction result. The method can make a reasonable purchase plan through the economic principle of the supply chain, is beneficial to fully utilizing resources by departments, reasonably distributing and purchasing the quantity of each spare part, and reduces unnecessary property cost and other operation cost.
Description
Technical Field
The invention relates to the technical field of computer application, in particular to a high-precision spare part demand prediction method.
Background
In the current rapidly-developing economic society, one of the ways for enterprises to obtain more competitive advantages is to utilize the existing capital more reasonably and to obtain more economic benefits, which is very important for the development of enterprises. The enterprise department can determine future spare part requirements through the prediction of the spare part requirements and key factors for adjusting the spare part requirements, grasp the future requirement trend in time, make reasonable planning and decision, and finally improve the overall competitive advantage and the economic benefit of enterprises.
In the existing mode, the traditional analysis and processing mode has high difficulty and inaccurate result. Therefore, a more accurate and effective high-precision spare part demand forecasting method is provided for the situation that factors influencing the spare part demand exist in a large quantity and are complicated and changeable, and the method has important significance for facilitating decision makers to make more reasonable plans and improving the overall competitiveness of enterprises.
Disclosure of Invention
The embodiment of the invention provides a high-precision spare part demand forecasting method, so as to accurately and effectively forecast the spare part demand. In order to achieve the purpose, the invention adopts the following technical scheme. A high-precision spare part demand prediction method comprises the following steps:
collecting metadata related to spare part demand prediction, and storing the metadata after ETL processing into a database;
preprocessing metadata stored in a database, wherein the preprocessing comprises data summarization, data integration and analysis processing;
performing data characteristic mining on the preprocessed metadata, determining each factor influencing the spare part requirement, analyzing the influence degree of each factor on the spare part requirement, and sequencing each factor according to the influence degree;
in the spare part demand forecasting stage, metadata with the calculated influence degree close to the influence degree after being processed by a key factor recognition algorithm is used as source data, the source data is input into a machine learning fusion modeling forecasting method based on Linear regression, AdaBoost and GBDT, the spare part demand of a certain month in the future is subjected to forecasting analysis, and a forecasting result is output.
The collecting metadata related to spare part demand forecasting and storing the metadata processed by the ETL into a database comprises the following steps:
configuring a data acquisition task, setting task attributes of the data acquisition task, wherein the task attributes comprise an acquisition object, acquisition time, an acquisition period and an audit level, executing the data acquisition task through a software program, and acquiring metadata from a data source of an enterprise department through data acquisition, exchange processing and data aggregation and import loading service functions; the metadata relates to various aspects of spare part information, and the data source is from various links from spare part production to spare part use; and carrying out ETL processing on the collected metadata, and storing the metadata after ETL processing into a database.
The metadata includes: basic information of each spare part, historical workload of consumed spare parts, inventory information of spare parts, purchasing information of spare parts, working environment of spare parts, maintenance information of spare parts, classification information of spare parts, maintenance information of spare parts, supply information of spare parts, consumption information of spare parts, and economic and vulnerability data of spare parts.
Preprocessing the metadata stored in the database, wherein the preprocessing comprises data summarization, data integration and analysis processing, and comprises the following steps:
the method comprises the steps that data collection, data integration and analysis processing are carried out on metadata stored in a database through a metadata management function, all links and various data in all stages are described in all directions through the metadata in the whole business process, the whole business process refers to the production, transportation, use, consumption and replacement links of spare parts, all the links comprise a supply link, a purchasing link, a transportation link, a production link, a use link and an overhaul link of the spare parts, and all the stages comprise all the stages of the use of the spare parts; the data summarization is used for checking the correctness and validity of the data.
The influencing factors comprise market supply quantity of spare parts, repair times, monthly consumption quantity of the spare parts, repair quantity, repair degree, purchase quantity, working time of spare part equipment, number of spare part suppliers, purchase unit price, maintenance effect, purchase times and maintenance times.
In the spare part demand prediction stage, metadata with an influence degree close to the front calculated after being processed by a key factor recognition algorithm is used as source data, the source data is input into a training model in a machine learning algorithm, a machine learning fusion modeling prediction method based on Linearregression, AdaBoost and GBDT is used for performing prediction analysis on the spare part demand of a certain future month, and a prediction result is output, and the method comprises the following steps: in the spare part demand prediction stage, a key factor recognition algorithm is used for eliminating useless influence factors, metadata with the influence degree calculated after the processing of the key factor recognition algorithm is used as source data, different types of influence factors are coded and then trained by using a machine learning fusion modeling prediction method based on Linear regression, AdaBoost and GBDT, the processed source data are input into the trained machine learning fusion modeling prediction method based on Linear regression, AdaBoost and GBDT, the spare part demand of a certain month in the future is subjected to prediction analysis, and the prediction result of the spare part demand is displayed on a front-end display platform through a report form, a chart and a map display mode.
The key factor identification algorithm is an XGboost algorithm model; the machine learning model comprises: a GBDT prediction model, a Linear regression prediction model and an AdaBoost prediction model.
According to the technical scheme provided by the embodiment of the invention, the spare part demand prediction obtained by the method provided by the embodiment of the invention has positive significance for department decision and planning, and a decision maker can make a reasonable purchase plan according to the prediction result and the supply chain economic principle, so that the method is beneficial to fully utilizing resources by departments, reasonably distributing the quantity of purchased spare parts and reducing unnecessary property cost and other operation cost.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is an implementation schematic diagram of a high-precision spare part demand prediction method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for predicting a high-precision spare part requirement according to an embodiment of the present invention;
fig. 3 is a processing flow chart of a machine learning fusion modeling prediction method for performing prediction analysis on the required quantity of a spare part, which is based on linear regression, AdaBoost and GBDT according to the embodiment of the present invention;
fig. 4 is a schematic diagram illustrating various factors influencing the requirement of a spare part according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention. As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
For the convenience of understanding the embodiments of the present invention, the following description will be further explained by taking several specific embodiments as examples in conjunction with the drawings, and the embodiments are not to be construed as limiting the embodiments of the present invention.
The spare part demand prediction is different from the demand prediction of general materials, because the spare part demand has great uncertainty and discontinuity type, if simply utilize simple prediction technique, the prediction result has great deviation with actual demand inevitably, leads to spare part stock excessive and makes the enterprise overstock a large amount of capital that flows, or the equipment shutdown loss that causes too little, influences the economic benefits of enterprise.
The embodiment of the invention provides a high-precision spare part demand forecasting method, and aims to solve the problems that the existing spare part demand forecasting method is complicated, the difference between a forecasting result and the actual situation is large, the reliability is low, and no complete spare part demand forecasting system is used for systematically forecasting and analyzing the demand quantity.
The spare part demand forecasting method carries out forecasting according to monthly time intervals, carries out spare part demand characteristic mining through the existing historical data, and forecasts the spare part demand quantity in the future month, so that a decision maker can quickly decide the spare part purchase quantity according to the supply chain relation, and the economic benefit is improved.
An implementation schematic diagram of a high-precision spare part demand prediction method provided by an embodiment of the present invention is shown in fig. 1, and a specific processing flow is shown in fig. 2, and the method includes the following processing steps:
step S10, collecting metadata related to the spare part demand forecast, and storing the metadata after ETL (Extract-Transform-Load) processing into a database.
In the data acquisition stage, metadata related to the demand forecast of the spare parts to be acquired is defined first, and the meaning and the standard of the metadata are determined.
Metadata is mainly data describing and defining the business data itself and its operating environment, such as describing databases, tables, columns, column attributes (types, formats, constraints, etc.), and so on. For the ETL process, the important significance of metadata is represented collectively as:
(1) defining the position of a data source and the attribute of the data source;
(2) determining a rule corresponding to the source data to the target data;
(3) determining relevant business logic;
(4) other necessary preparation work before the data is actually loaded. Metadata generally runs throughout the data warehouse project, and all processes of ETL must maximally reference metadata. Reasonable metadata can effectively depict the relevance of information, and the ETL process can be more effectively guided by combining the relevance of information with the data quality.
In the present application, the metadata mainly includes basic information of each spare part, historical workload of consumed spare parts, inventory information of spare parts, procurement information of spare parts, working environment of spare parts, maintenance information of spare parts, classification information of spare parts, maintenance information of spare parts, supply information of spare parts, consumption information of spare parts, economic efficiency and vulnerability of spare parts, and other basic data. Metadata is the "command center" of the ETL process, so the selection, specification and management of metadata directly affect the correctness and efficiency of the ETL process.
And configuring a data acquisition task, flexibly adjusting the acquisition task according to the actual condition of the data, and setting task attributes of the data acquisition task, such as acquisition object, acquisition time, acquisition period, audit level and the like.
The data acquisition task is executed through a software program, and metadata is acquired from a data source of an enterprise department through service functions of data acquisition, exchange processing, data summarization, import loading and the like. In practical application, a relational database is frequently adopted as a data source, and other data sources also have file forms, such as txt files, excel files, xml files, PDF files, and the like.
From the metadata, it can be known that the metadata to be collected relates to various aspects of spare part information, and information needs to be collected from various links from production to use of the spare part. The data source for metadata collection therefore comes from various links from the production of the spare part to the use of the spare part. The used modes include manual recording and machine scanning, information is synchronized in a database, and an ETL tool is used for cleaning data to meet the use requirement.
Because the metadata collected from the data source does not necessarily completely satisfy the requirements of the database, ETL processing is performed on the collected metadata. And storing the metadata after ETL processing into a database so as to summarize and analyze the metadata.
An ETL system needs to be able to complete the periodic automatic loading of daily data within a limited time, support the loading of initial data and historical data, and meet the requirements for future expansion. Dozens or more target data tables and a considerable amount of source data in the system mean the complexity of an ETL program, the operation efficiency of the system needs to be fully considered due to huge data volume, and a flexible, simple and clear program structure is required for developing a complex program conveniently; the requirement for optimizing the efficiency of the program often requires personalized design for different data. Therefore, the design of the ETL must strike a balance between manageability and program performance of the development.
And step S20, preprocessing the metadata stored in the database, wherein the preprocessing comprises data summarization, data integration and analysis processing.
The metadata stored in the database is subjected to data summarization, data integration and analysis processing through a metadata management function, and various data existing in each link and each stage are comprehensively described through the metadata in the whole business process, so that data information in the system can be read and managed in the whole process.
The whole business process refers to links of production, transportation, use, consumption, replacement and the like of the spare parts, and comprises a complete life cycle of the spare parts, so that each link of the spare parts is ensured to be considered, and the accuracy of the spare part model prediction is convenient to improve. Wherein, each link mainly relates to a supply link (including information such as market supply quantity, supplier quantity, lowest supply unit price, highest supply unit price and spare part acquisition difficulty) of spare parts, a purchase link (including information such as spare part purchase quantity, purchase frequency, purchase unit price, purchase standard and spare part shortage cost), a transportation link (including information such as spare part transportation cost and spare part storage cost), a production link (including information such as a spare part manufacturer, a technical specification, spare part material, whether standard, spare part material, a class of spare parts, spare part equipment working time, generating equipment working strength and the like), a use link (including information such as spare part importance, spare part replaceability, inventory environment, spare part working temperature, spare part working strength, spare part working position and spare part vulnerability) and a maintenance link (including information such as spare part repair frequency, Information such as the number of spare parts repaired, the degree of repair, the number of times of maintenance, and the effect of maintenance); each stage is for the use of spare parts, such as manufacturing, shipping, procurement, use, and overhaul.
Data summarization is a comprehensive method for overall data assurance and data audit, and is used for auditing the correctness and validity of data. For the demand forecasting work, the function of summarizing and examining data is important, and the data is the basis of demand forecasting when being correct and effective. The data summarization service mainly realizes the automatic summarization function of the collected data through a summarization rule customized by the system, generates a summarized data report and provides export printing. Then, the data is converted by the data conversion loading service and then stored in a database of the system, and original data of a reporting unit is finally saved as files.
The purpose of the ETL processing and preprocessing of metadata is to guarantee timeliness, legality, integrity, consistency, auditability and security of data and management of the platform.
And step S30, performing data feature mining on the preprocessed metadata, determining each factor influencing the spare part requirement, analyzing the influence degree of each factor on the spare part requirement, and sequencing each factor according to the influence degree.
Fig. 4 is a schematic diagram of various factors influencing the requirement of a spare part according to an embodiment of the present invention. There are many factors that affect the data, and as shown in fig. 4, it can be seen that the factors that affect the result are related to the spare part market supply amount, the number of repairs, the spare part monthly consumption amount, the number of repairs, the degree of repairs, the number of purchases, the spare part equipment operating time, the number of spare part suppliers, the purchase unit price, the maintenance effect, the number of purchases, and the number of maintenance.
Step S40, in the stage of spare part demand prediction, a key factor recognition algorithm can be used for eliminating useless influence factors, training characteristics are reduced, and the model training effect is improved. The method comprises the steps of taking the metadata with the influence degree close to the front, the useful influence factors and the influence degree of the sequenced influence factors on the spare part requirement, which are calculated after the influence degree analysis processing, as source data, processing the metadata by adopting encoding modes such as One-hotencoding and Label-encoding and the like for different types of factors, inputting the processed metadata into a machine learning fusion modeling prediction method based on LinearReggression, AdaBoost and GBDT, performing prediction analysis on the spare part requirement quantity of a certain future month, and outputting a prediction result.
The more useless features in the machine learning affect the generalization capability and learning time of the model, and the sequenced influence factors are used for training the machine learning fusion modeling prediction method based on Linear regression, AdaBoost and GBDT, so that the machine learning precision can be obviously improved, the model training time is reduced, and the problem of dimensional disaster is effectively avoided. And 3, the dimension disaster problem is relieved: the more features, the more complex the model is, and the generalization ability is reduced. The difficulty of the learning task is reduced: the larger the number of features, the longer the time required to analyze the features and train the model.
The essence of machine learning is function learning, the existing data characteristics and prediction results are subjected to model training and modeling by using a machine learning algorithm, a function which can be used for calculation, namely the algorithm model, is obtained finally, and the data characteristics needing to be predicted are input into the function to obtain the prediction results.
In the system, XGboost algorithm model algorithm is used for model training, key features in data are extracted, and influence caused by useless features is reduced. And then calling a GBDT prediction model, a Linear regression prediction model and an AdaBoost prediction model to perform multi-model fusion training and prediction, so that the accuracy of the spare part demand prediction is improved. Then, the prediction result of the spare part demand can be displayed on the front-end display platform through the modes of report forms, charts, map display and the like, so that a user can conveniently and quickly check the prediction result.
The front-end display platform adopts a B/S framework, is composed of a whole set of components or services, and is connected through a powerful Web-based communication framework, so that different application requirements of an application user are met. The front-end display platform can adopt Jquery, JS and other page display technologies.
The machine learning fusion modeling prediction method based on Linear regression, AdaBoost and GBDT is realized by performing algorithm through a programming language.
The processing flow chart of the machine learning fusion modeling prediction method based on linear regression, AdaBoost and GBDT for performing prediction analysis on the spare part demand quantity is shown in FIG. 3. In the whole process of predicting the demand of the spare parts, the system platform integrates related prediction functions to realize configuration management. The presentation forms of data, tools, algorithms and functions required by prediction and analysis results can be defined by self, so that an extensible analysis platform is provided for users to perform analysis activities.
A large number of mathematical operations are involved in the required programming of algorithmic design problems and data analysis processes. Although the modern mathematical theory of numerical calculation is well developed, most of the calculation problems have efficient standard solutions, the amount of calculation for simulating a complex model by a computer is still large. At present, the international popular universal engineering calculation software R/Python and other languages cover a model fitting tool, and a solution is provided for the problem.
The machine learning fusion modeling prediction method based on LinearRegulation, AdaBoost and GBDT well writes corresponding calculation functions by utilizing Python/R language and then packs the calculation functions into jar packets for Java calling. And calling basic data in the basic data management function module and a model implementation algorithm of the prediction model management module by a system user so as to implement prediction, and providing the prediction data to the spare part requirement analysis module for display to the user.
The client side of the spare part demand prediction system utilizes visualization and user interaction technology, integrates inquiry, statistics, data mining and analysis, and establishes and perfects a data collection and data updating mechanism by collecting and integrating basic data and special information of basic information of each spare part, historical task workload of consumed spare parts, inventory information of spare parts, purchase information of spare parts, working environment of spare parts, maintenance information of spare parts, classification information of spare parts, maintenance information of spare parts, supply information of spare parts, consumption information of spare parts, economy and vulnerability of spare parts and the like, so as to establish the spare part demand prediction system, observe the demand condition of enterprise spare parts, fully reflect the demand condition of enterprises on different spare parts in different time periods, and achieve the purpose of 'free view of resource demand'. By means of a visual interface and a data management technology, a friendly man-machine interaction interface is directly provided for users, and non-professional management and decision-making personnel can operate conveniently. By fusing various machine learning model prediction technologies (including a GBDT prediction model, a Linear regression prediction model and an AdaBoost prediction model), the data are subjected to omnibearing data model training, the data are predicted, data sharing and informatization services are provided for relevant departments, and support is provided for management decisions of enterprises. The system is designed according to user requirements, data patterns and expert knowledge of a knowledge base and related software engineering standards, and is realized by programming through a development tool.
In conclusion, the spare part demand prediction obtained by the method of the embodiment of the invention has positive significance on department decision and planning, and a decision maker can make a reasonable purchase plan according to the prediction result and the economic principle of a supply chain, so that the method is beneficial to making full use of resources by departments, reasonably distributing and purchasing the quantity of each spare part, and reducing unnecessary property cost and other operation cost, thereby achieving the purposes of saving cost, focusing on more needed spare parts and finally improving the income of the departments.
The accuracy of the spare part demand prediction result obtained by the method provided by the embodiment of the invention has great influence on department decision, and the inaccurate prediction result can generate greater loss to the department, so that the improvement and innovation of the traditional method are important for overcoming the defects and deficiencies or introducing a new method, and therefore, the method for enhancing the research on the spare part demand prediction has practical significance and strong social and economic values.
Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for apparatus or system embodiments, since they are substantially similar to method embodiments, they are described in relative terms, as long as they are described in partial descriptions of method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110411100.3A CN113127538B (en) | 2021-04-16 | 2021-04-16 | High-precision spare part demand prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110411100.3A CN113127538B (en) | 2021-04-16 | 2021-04-16 | High-precision spare part demand prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113127538A true CN113127538A (en) | 2021-07-16 |
| CN113127538B CN113127538B (en) | 2024-02-09 |
Family
ID=76777034
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110411100.3A Active CN113127538B (en) | 2021-04-16 | 2021-04-16 | High-precision spare part demand prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113127538B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115081967A (en) * | 2022-08-22 | 2022-09-20 | 中科航迈数控软件(深圳)有限公司 | Method and system for simulating machining process of numerical control machine tool based on multi-dimensional perception |
| CN115375250A (en) * | 2022-10-27 | 2022-11-22 | 河北东来工程技术服务有限公司 | Method and system for managing spare parts of ship |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001063457A2 (en) * | 2000-02-22 | 2001-08-30 | I2 Technologies, Inc. | Electronic marketplace providing service parts inventory planning and management |
| CN108898245A (en) * | 2018-06-15 | 2018-11-27 | 上海探能实业有限公司 | A kind of needing forecasting method for Wind turbines components |
| CN108960588A (en) * | 2018-06-15 | 2018-12-07 | 上海探能实业有限公司 | A kind of integrated evaluating method for Wind turbines standby redundancy |
| KR101966558B1 (en) * | 2017-12-08 | 2019-04-05 | 세종대학교산학협력단 | System and method for visualizing equipment inventory status and repair parts procurement request |
| CN111489037A (en) * | 2020-04-14 | 2020-08-04 | 青海绿能数据有限公司 | An optimization method of spare parts storage strategy for new energy wind turbines based on demand forecast |
-
2021
- 2021-04-16 CN CN202110411100.3A patent/CN113127538B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001063457A2 (en) * | 2000-02-22 | 2001-08-30 | I2 Technologies, Inc. | Electronic marketplace providing service parts inventory planning and management |
| KR101966558B1 (en) * | 2017-12-08 | 2019-04-05 | 세종대학교산학협력단 | System and method for visualizing equipment inventory status and repair parts procurement request |
| CN108898245A (en) * | 2018-06-15 | 2018-11-27 | 上海探能实业有限公司 | A kind of needing forecasting method for Wind turbines components |
| CN108960588A (en) * | 2018-06-15 | 2018-12-07 | 上海探能实业有限公司 | A kind of integrated evaluating method for Wind turbines standby redundancy |
| CN111489037A (en) * | 2020-04-14 | 2020-08-04 | 青海绿能数据有限公司 | An optimization method of spare parts storage strategy for new energy wind turbines based on demand forecast |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115081967A (en) * | 2022-08-22 | 2022-09-20 | 中科航迈数控软件(深圳)有限公司 | Method and system for simulating machining process of numerical control machine tool based on multi-dimensional perception |
| CN115081967B (en) * | 2022-08-22 | 2022-11-29 | 中科航迈数控软件(深圳)有限公司 | Method and system for simulating machining process of numerical control machine tool based on multi-dimensional perception |
| CN115375250A (en) * | 2022-10-27 | 2022-11-22 | 河北东来工程技术服务有限公司 | Method and system for managing spare parts of ship |
| CN115375250B (en) * | 2022-10-27 | 2023-01-06 | 河北东来工程技术服务有限公司 | Method and system for managing spare parts of ship |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113127538B (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108932589B (en) | Enterprise informatization project implementation management system | |
| Usenko et al. | Formation of an integrated accounting and analytical management system for value analysis purposes | |
| US20080319811A1 (en) | System and method for modeling an asset-based business | |
| JP2021068435A (en) | Supplier evaluation device and supplier evaluation method | |
| Shrouf et al. | Multi-level awareness of energy used in production processes | |
| US20070021992A1 (en) | Method and system for generating a business intelligence system based on individual life cycles within a business process | |
| JP2022035965A (en) | Intelligent supplier managing system and intelligent supplier managing method | |
| CN113127537B (en) | Spare part demand prediction method integrating time sequence prediction model and machine learning model | |
| CN115496337A (en) | Data system for supporting brain of enterprise | |
| CN113127538B (en) | High-precision spare part demand prediction method | |
| Denysenko et al. | Implementation of CALS-technologies in quality management of product life cycle processes | |
| CN116976948A (en) | Method and system for generating dynamic feedback flow diagram of full value chain of manufacturing enterprise | |
| CN112488425A (en) | Prediction method for bank business process task template optimization | |
| CN111915100B (en) | High-precision freight prediction method and freight prediction system | |
| CN118071374A (en) | Full life cycle industrial product carbon emission accounting and carbon transaction method | |
| Saputra et al. | An Effective Open ERP System for Automation in Financial Reporting for SMEs based on Service Oriented Architecture | |
| CN115496462A (en) | A system platform that realizes intelligent management and control of right-of-use assets throughout their life cycle | |
| Mutschler et al. | An approach to quantify the costs of business process intelligence | |
| RU2020139765A (en) | The system for implementing the method of matrix-digital transformation of a variable set of data for generating a situational-strategic product program | |
| Radhakrishnan et al. | The role of business intelligence in organizational sustainability in the era of IR 4.0 | |
| CN110556181A (en) | large medical equipment budget declaration method | |
| Mutschler et al. | A Survey on Economic-driven Evaluations of Information Technology | |
| Das | Applications of management information system in an organization | |
| CN118469331B (en) | A deep learning-based evaluation method for digital construction projects | |
| Zou et al. | Pioneering ESG Evaluation: A Cloud-Based Framework Leveraging Machine Learning and Domain-Driven Design |
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 |