CN114219343A - Part prediction method based on data analysis and intelligent algorithm - Google Patents
Part prediction method based on data analysis and intelligent algorithm Download PDFInfo
- Publication number
- CN114219343A CN114219343A CN202111585844.3A CN202111585844A CN114219343A CN 114219343 A CN114219343 A CN 114219343A CN 202111585844 A CN202111585844 A CN 202111585844A CN 114219343 A CN114219343 A CN 114219343A
- Authority
- CN
- China
- Prior art keywords
- prediction
- configuration
- vehicle
- algorithm
- forecasting
- 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.)
- Pending
Links
Images
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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
A part prediction method based on data analysis and intelligent algorithm comprises the following steps that S1, an order manufacturing management system sends historical actual order vehicle type configuration information and actual part usage information to a prediction platform; step S2, the forecasting platform manages the configuration, forecasting time and quantity of market concern items of different versions, configures the combination mode and weight of the algorithm, carries out forecasting calculation and sends the calculated forecasting result to the engineering system; step S3, the engineering system deduces necessary configuration items according with engineering rules through the input prediction results, and gives a part list necessarily associated with the configuration items; and step S4, the prediction platform distributes the prediction result to the responding supplier through the distribution platform. The method improves the coverage rate of the prediction range of the part to more than 99 percent; the prediction accuracy reaches 56% on average, and the prediction accuracy of key parts reaches 70%.
Description
Technical Field
The invention belongs to the technical field of automobile manufacturing, and particularly relates to a part prediction method based on data analysis and an intelligent algorithm.
Background
The market division gives the specifically configured vehicle models in a list of marketable vehicle models for the manufacturing engineering division and provides the predicted time and quantity. And the planning logistics part develops the manufacturing BOM corresponding to the specific vehicle type through the predicted vehicle type and the provided prediction time to obtain the required part summarizing requirement.
After the vehicle model is selected by C2B, the vehicle model selected by the user increases exponentially, the manufacturing engineering department cannot list all manufacturable vehicle models in advance, and the market department cannot predict the accurate vehicle model and only can predict the market attention configuration. The prediction of partial configuration can only calculate the part requirements of the partial configuration, and can not meet the prediction that the logistics department hopes to have all parts.
Disclosure of Invention
The technical problem to be solved by the invention is to overcome the defects of the prior art, and provide a part prediction method based on data analysis and intelligent algorithm, wherein summary information of a prediction platform is built, and the part prediction information is calculated through a prediction algorithm.
The invention provides a part prediction method based on data analysis and an intelligent algorithm, which comprises the following steps,
step S1, the order manufacturing management system sends the order vehicle type configuration information and the actual part usage information which actually occur in history to the prediction platform;
step S2, the forecasting platform manages the configuration, forecasting time and quantity of market concern items of different versions, configures the combination mode and weight of the algorithm, carries out forecasting calculation and sends the calculated forecasting result to the engineering system;
step S3, the engineering system deduces necessary configuration items according with engineering rules through the input prediction results, and gives a part list necessarily associated with the configuration items;
and step S4, the prediction platform distributes the prediction result to the responding supplier through the distribution platform.
As a further technical scheme of the invention, the prediction platform replaces a part list according to the actual part usage and the new part breaking point in the order manufacturing management system, obtains the range of the part to be predicted, and calculates according to the algorithms of ARIMA and LSTM neural network models and the like with set and adjusted parameters in the system to obtain the part requirement.
Further, in step S2, the algorithm is configured to integrate the auto-regressive moving average model and the LSTM long and short term memory network seasonally by ARIMA; the weights are each 0.5;
wherein, the parameter meaning in ARIMA algorithm: (p, d, q); (P, D, Q). Here, (P, D, Q) are non-seasonal parameters, while (P, D, Q) follow the same definition, applied to the seasonal component of the time series; p is the number of autoregressive terms; q is the number of the moving average terms; d is the number of differences (order) made to make it a stationary sequence;
parametric implications in the LSTM algorithm: input _ size, input feature dimension, namely the number of input elements in each row; hidden _ size, namely the dimension of the hidden layer state, namely the number of hidden layer nodes; num _ layers is the number of layers of the LSTM stack; bias, whether the hidden layer state has deviation; batch _ first, whether the first dimension of input and output is batch size; dropout, whether a dropout layer is added after other RNN layers except the last RNN layer; bidirectional is whether it is a bi-directional RNN.
Further, the order vehicle type configuration information includes the perception configuration items of the customer, such as tires, a base machine, whether a skylight exists or not, and the like; and key vehicle configuration items such as engine, transmission, shaft length, etc.
Further, in step S3, first, the engineering system deduces the complete configuration of the vehicle according to the principle that the current configuration breakpoint is valid, based on the input results of the customer perception and the key configuration of the vehicle; secondly, according to the complete vehicle configuration list, a part list related to the vehicle configuration item is given by analyzing UC constraints (namely, the AND or NOT relation of a plurality of configurations) on the vehicle BOM row.
The method has the beneficial effects that the coverage rate of the prediction range of the part is improved to be more than 99%; the prediction accuracy reaches 56% on average, and the prediction accuracy of key parts reaches 70%.
Drawings
FIG. 1 is a schematic flow chart of the operation of the present invention.
Detailed Description
Referring to fig. 1, the present embodiment provides a part prediction method based on data analysis and intelligent algorithm, including the following steps,
step S1, the order manufacturing management system sends the order vehicle type configuration information and the actual part usage information which actually occur in history to the prediction platform;
step S2, the forecasting platform manages the configuration, forecasting time and quantity of market concern items of different versions, configures the combination mode and weight of the algorithm, carries out forecasting calculation and sends the calculated forecasting result to the engineering system;
step S3, the engineering system deduces necessary configuration items according with engineering rules through the input prediction results, and gives a part list necessarily associated with the configuration items;
and step S4, the prediction platform distributes the prediction result to the responding supplier through the distribution platform.
And the prediction platform is used for manufacturing the new part according to the actual part consumption in the management system, breaking off the new part, replacing the part list, acquiring the range of the part to be predicted, calculating according to algorithms such as ARIMA (autoregressive integrated moving average) and LSTM (least squares) neural network models with set and adjusted parameters in the system and the like, and acquiring the part requirement.
In step S2, in step S2, the configuration algorithm is ARIMA seasonally integrated autoregressive moving average model and LSTM long and short term memory network; the weights are each 0.5;
wherein, the parameter meaning in ARIMA algorithm: (p, d, q); (P, D, Q). Here, (P, D, Q) are non-seasonal parameters, while (P, D, Q) follow the same definition, applied to the seasonal component of the time series; p is the number of autoregressive terms; q is the number of the moving average terms; d is the number of differences (order) made to make it a stationary sequence;
parametric implications in the LSTM algorithm: input _ size, input feature dimension, namely the number of input elements in each row; hidden _ size, namely the dimension of the hidden layer state, namely the number of hidden layer nodes; num _ layers is the number of layers of the LSTM stack; bias, whether the hidden layer state has deviation; batch _ first, whether the first dimension of input and output is batch size; dropout, whether a dropout layer is added after other RNN layers except the last RNN layer; bidirectional is whether it is a bi-directional RNN.
The order vehicle type configuration information comprises perception configuration items of a client, such as tires, a base machine, whether a skylight exists or not and the like; and key vehicle configuration items such as engine, transmission, shaft length, etc.
Further, in step S3, first, the engineering system deduces the complete configuration of the vehicle according to the principle that the current configuration breakpoint is valid, based on the input results of the customer perception and the key configuration of the vehicle; secondly, according to the complete vehicle configuration list, a part list related to the vehicle configuration item is given by analyzing UC constraints (namely, the AND or NOT relation of a plurality of configurations) on the vehicle BOM row.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are intended to further illustrate the principles of the invention, and that various changes and modifications may be made without departing from the spirit and scope of the invention, which is intended to be protected by the appended claims. The scope of the invention is defined by the claims and their equivalents.
Claims (5)
1. A part prediction method based on data analysis and intelligent algorithm is characterized by comprising the following steps,
step S1, the order manufacturing management system sends the order vehicle type configuration information and the actual part usage information which actually occur in history to the prediction platform;
step S2, the forecasting platform manages the configuration, forecasting time and quantity of market concern items of different versions, configures the combination mode and weight of the algorithm, carries out forecasting calculation and sends the calculated forecasting result to the engineering system;
step S3, the engineering system deduces necessary configuration items according with engineering rules through the input prediction results, and gives a part list necessarily associated with the configuration items;
and step S4, the prediction platform distributes the prediction result to the responding supplier through the distribution platform.
2. The method as claimed in claim 1, wherein the prediction platform obtains the range of the predicted part according to the actual part usage in the order manufacturing management system, breaking off new parts, replacing part list, and calculating according to the algorithms such as ARIMA and LSTM neural network models with set and adjusted parameters in the system to obtain the part demand.
3. The method for predicting parts based on data analysis and intelligent algorithm as claimed in claim 1, wherein in step S2, the configuration algorithm is ARIMA seasonally integrated autoregressive moving average model and LSTM long-short term memory network; the weights are each 0.5; wherein, the parameter meaning in ARIMA algorithm: (p, d, q); (P, D, Q); here, (P, D, Q) are non-seasonal parameters, while (P, D, Q) follow the same definition, applied to the seasonal component of the time series; p is the number of autoregressive terms; q is the number of the moving average terms; d is the number of differences (order) made to make it a stationary sequence;
parametric implications in the LSTM algorithm: input _ size, input feature dimension, namely the number of input elements in each row; hidden _ size, namely the dimension of the hidden layer state, namely the number of hidden layer nodes; num _ layers is the number of layers of the LSTM stack; bias, whether the hidden layer state has deviation; batch _ first, whether the first dimension of input and output is batch size; dropout, whether a dropout layer is added after other RNN layers except the last RNN layer; bidirectional is whether it is a bi-directional RNN.
4. The part prediction method based on the data analysis and intelligent algorithm as claimed in claim 1, wherein the configuration information of the vehicle type in order comprises a perception configuration item of a customer and a key configuration item of the vehicle.
5. The method for predicting parts based on data analysis and intelligent algorithm as claimed in claim 1, wherein in step S3, the engineering system derives the complete configuration of the vehicle according to the principle that the current configuration breakpoint is valid, based on the input results of the customer perception and the key configuration of the vehicle; and secondly, according to the complete vehicle configuration list, a part list related to the vehicle configuration item is given by analyzing UC constraints on the vehicle BOM line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111585844.3A CN114219343A (en) | 2021-12-23 | 2021-12-23 | Part prediction method based on data analysis and intelligent algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111585844.3A CN114219343A (en) | 2021-12-23 | 2021-12-23 | Part prediction method based on data analysis and intelligent algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114219343A true CN114219343A (en) | 2022-03-22 |
Family
ID=80705359
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111585844.3A Pending CN114219343A (en) | 2021-12-23 | 2021-12-23 | Part prediction method based on data analysis and intelligent algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114219343A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115774182A (en) * | 2022-12-05 | 2023-03-10 | 安测半导体技术(义乌)有限公司 | ATE platform-based chip testing method and device |
-
2021
- 2021-12-23 CN CN202111585844.3A patent/CN114219343A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115774182A (en) * | 2022-12-05 | 2023-03-10 | 安测半导体技术(义乌)有限公司 | ATE platform-based chip testing method and device |
| CN115774182B (en) * | 2022-12-05 | 2023-10-13 | 安测半导体技术(义乌)有限公司 | Chip testing method and device based on ATE platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109784806B (en) | Supply chain control method, system and storage medium | |
| US10896203B2 (en) | Digital analytics system | |
| JP6926008B2 (en) | Maintenance planning equipment and maintenance planning method | |
| Naeem et al. | Production planning optimization for manufacturing and remanufacturing system in stochastic environment | |
| US10740773B2 (en) | Systems and methods of utilizing multiple forecast models in forecasting customer demands for products at retail facilities | |
| Islam et al. | Energy demand forecasting | |
| WO2002037376A1 (en) | Supply chain demand forecasting and planning | |
| WO2019049546A1 (en) | Prediction system and method | |
| Amer et al. | Optimizing order fulfillment using design for six sigma and fuzzy logic | |
| Rakićević et al. | Focus forecasting in supply chain: the case study of fast moving consumer goods company in Serbia | |
| Mahbub et al. | A neural approach to product demand forecasting | |
| Ewbank et al. | Sustainable resource management in a supply chain: a methodological proposal combining zero-inflated fuzzy time series and clustering techniques | |
| CN114219343A (en) | Part prediction method based on data analysis and intelligent algorithm | |
| Alsyouf et al. | On preventive maintenance policies: a selection framework | |
| CN113469595A (en) | Intelligent supply chain system and server platform | |
| Hung et al. | Capacity rationing decision procedures with order profit as a continuous random variable | |
| Kamhuber et al. | An efficient hybrid multi-criteria optimization approach for rolling production smoothing of a European food manufacturer | |
| JP2001134643A (en) | Device and method for predicting demand | |
| Azadi et al. | Developing a WPF-CCR model for selecting suppliers in the presence of stochastic data | |
| Ren et al. | Anticipatory shipping versus emergency shipment: data-driven optimal inventory models for online retailers | |
| CN113762842A (en) | Warehouse scheduling method, server and system | |
| Makarova et al. | Planning of the spare parts supply in the system of corporate service automotive company abroad | |
| Makarova et al. | Intellectualization of the spare parts supplier selection by the analysis of multi-criterial solutions | |
| Pérez-Gallardo et al. | Methodology for supply Chain integration: a case study in the Artisan Industry of footwear | |
| Hadad et al. | A revised method for allocating the optimum number of similar machines to operators |
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 |