CN117273422B - Supply chain cooperative control method and system for digital production - Google Patents
Supply chain cooperative control method and system for digital production Download PDFInfo
- Publication number
- CN117273422B CN117273422B CN202311571719.6A CN202311571719A CN117273422B CN 117273422 B CN117273422 B CN 117273422B CN 202311571719 A CN202311571719 A CN 202311571719A CN 117273422 B CN117273422 B CN 117273422B
- Authority
- CN
- China
- Prior art keywords
- node
- supply chain
- abnormal
- anomaly
- probability
- 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 91
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000007726 management method Methods 0.000 claims abstract description 57
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 230000002159 abnormal effect Effects 0.000 claims description 138
- 230000005856 abnormality Effects 0.000 claims description 40
- 238000004364 calculation method Methods 0.000 claims description 20
- 238000011084 recovery Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 15
- 238000012384 transportation and delivery Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000002195 synergetic effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000013068 supply chain management Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0633—Workflow 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a supply chain collaborative management and control method and a system for digital production, which relate to the technical field of data processing, wherein the method comprises the following steps: the method comprises the steps of acquiring production supply chain nodes, acquiring real-time shared data of the production supply chain nodes, carrying out node anomaly analysis on production data sets of N supply chain nodes, positioning a first anomaly node and anomaly probability of the first anomaly node, taking anomaly probability difference of the first anomaly node and expected anomaly probability as an equalization target, inputting the first anomaly node as a Nash equalization node into a trained collaborative equalization management and control model in advance to carry out collaborative equalization identification on the N supply chain nodes, and obtaining N equalization decision results based on one-to-one correspondence of the N supply chain nodes.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a supply chain collaborative management and control method and system for digital production.
Background
With the development of science and technology, particularly the development of the field of supply chains, in the digital age, enterprises can utilize various digital means including internet of things, cloud computing, artificial intelligence and the like to realize optimization of collaborative management of the supply chains. The Internet of things technology is widely applied, and enterprises can monitor all links of the whole supply chain in real time through the Internet of things technology, so that the problems of transportation, storage and the like are timely found and solved. Meanwhile, the Internet of things technology can also achieve the effects of information sharing and communication, so that the whole supply chain management is more synergistic and efficient, and the technical problem of low synergistic management and control efficiency caused by insufficient management and control of nodes in a supply chain in the prior art exists.
Disclosure of Invention
The application provides a supply chain collaborative management and control method and a supply chain collaborative management and control system for digital production, which are used for solving the technical problem that the collaborative management and control efficiency is low due to insufficient management and control of nodes in a supply chain in the prior art.
In view of the foregoing, the present application provides a supply chain collaborative management method and system for digital production.
In a first aspect, the present application provides a supply chain collaborative management method for digital production, the method comprising: acquiring a production supply chain node, wherein the production supply chain link node is a full-flow supply chain node for producing a target product; collecting real-time shared data of the production supply chain nodes to obtain production data sets of N supply chain nodes; carrying out node anomaly analysis by using the production data set, and positioning a first anomaly node and anomaly probability of the first anomaly node, wherein the first anomaly node is a node with the highest anomaly probability in the N supply chain nodes; taking the abnormal probability difference between the abnormal probability of the first abnormal node and the expected abnormal probability as an equalization target, and taking the first abnormal node as a Nash equalization node to input a cooperative equalization control model trained in advance; and carrying out collaborative balance identification on the N supply chain nodes by adopting the collaborative balance management and control model to obtain N balance decision results based on one-to-one correspondence of the N supply chain nodes.
In a second aspect, the present application provides a supply chain collaborative management system for digital production, the system comprising: the node determining module is used for acquiring production supply chain nodes, and the production supply chain link nodes are full-flow supply chain nodes for producing target products; the data acquisition module is used for acquiring real-time shared data of the production supply chain nodes and acquiring production data sets of N supply chain nodes; the node anomaly analysis module is used for carrying out node anomaly analysis by utilizing the production data set and positioning a first anomaly node and the anomaly probability of the first anomaly node, wherein the first anomaly node is the node with the highest anomaly probability in the N supply chain nodes; the model training module is used for taking an abnormal probability difference between the abnormal probability of the first abnormal node and the expected abnormal probability as an equalization target, and taking the first abnormal node as a Nash equalization node to input a cooperative equalization control model trained in advance; and the collaborative balance identification module is used for carrying out collaborative balance identification on the N supply chain nodes by adopting the collaborative balance management and control model to obtain N balance decision results based on the N supply chain nodes in one-to-one correspondence.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the supply chain collaborative management and control method and system for digital production, which are provided by the application, relate to the technical field of data processing, solve the technical problems of low collaborative management and control efficiency caused by insufficient management and control of nodes in a supply chain in the prior art, realize reasonable and accurate management and control of the nodes in the supply chain, and improve collaborative management and control efficiency.
Drawings
FIG. 1 is a schematic flow diagram of a supply chain collaborative management and control method for digital production provided in the present application;
FIG. 2 is a schematic diagram of a first abnormal node flow in a supply chain collaborative management and control method for digital production;
FIG. 3 is a schematic diagram of a process flow of expected anomaly probabilities in a supply chain collaborative management and control method for digital production;
fig. 4 is a schematic diagram of a supply chain collaborative management and control system for digital production.
Reference numerals illustrate: the system comprises a node determining module 1, a data acquisition module 2, a node anomaly analysis module 3, a model training module 4 and a cooperative equalization identification module 5.
Detailed Description
The application provides a supply chain collaborative management and control method and a supply chain collaborative management and control system for digital production, which are used for solving the technical problem that the collaborative management and control efficiency is low due to insufficient management and control of nodes in a supply chain in the prior art.
Example 1
As shown in fig. 1, an embodiment of the present application provides a supply chain collaborative management method for digital production, the method comprising:
step A100: acquiring a production supply chain node, wherein the production supply chain link node is a full-flow supply chain node for producing a target product;
in this application, the supply chain collaborative management and control method for digital production provided in this application is applied to a supply chain collaborative management and control system for digital production, in order to ensure collaborative management and control of a supply chain for digital production, operation nodes in the supply chain are first required to be determined and acquired, the operation nodes of the supply chain are all process nodes included in the supply chain, which are collectively referred to as production supply nodes, and the production supply chain link points are all process supply chain nodes for producing a target product, and in all process supply chain nodes, purchasing nodes, production nodes, inventory management nodes, logistics nodes, distribution nodes, after-sales nodes and the like for producing the product can be included, so that collaborative management and control of the supply chain for digital production is realized for later period as an important reference basis.
Step A200: collecting real-time shared data of the production supply chain nodes to obtain production data sets of N supply chain nodes;
in the application, in order to perform collaborative management and control on the supply chain more accurately, the determined production supply chain nodes are required to be used as a data reference basis, real-time shared data contained in each of the production supply chain nodes is collected, the real-time shared data contains real-time purchasing data, real-time production data, real-time inventory management data, real-time logistics data, real-time distribution data, real-time after-sales data and the like of production products, real-time data recorded in all the nodes are subjected to public interaction in the system, and meanwhile, data integration is performed according to all the collected real-time shared data, so that a production data set of N supply chain nodes is generated, wherein N is an integer greater than 3, and further, collaborative management and control on the supply chain for digital production is guaranteed.
Step A300: carrying out node anomaly analysis by using the production data set, and positioning a first anomaly node and anomaly probability of the first anomaly node, wherein the first anomaly node is a node with the highest anomaly probability in the N supply chain nodes;
further, as shown in fig. 2, step a300 of the present application further includes:
step a310: identifying according to the production data set to obtain N supply abnormality probabilities based on N supply chain nodes, wherein the supply abnormality probabilities are abnormal delay probabilities representing that each supply chain node is based on a delivery cycle of arrival;
step A320: and carrying out peak deviation anomaly analysis on the N supply anomaly probabilities, and positioning the first anomaly node.
Further, step a320 of the present application includes:
step A321: collecting historical supply abnormal events of the N supply chain nodes;
step A322: analyzing the historical supply abnormal events to obtain N historical abnormal recovery indexes corresponding to the N supply chain nodes, wherein the historical abnormal recovery indexes represent emergency recovery capacity of the supply chain nodes when the abnormal events occur;
step A323: and adjusting the N supply abnormality probabilities according to the N historical abnormality recovery indexes.
In the present application, in order to improve the accuracy of collaborative management of digitally produced supply chains, therefore, it is necessary to perform intra-node anomaly analysis on the production supply chain nodes by using the obtained production data sets of the N supply chain nodes, and performing anomaly analysis on the N supply anomaly probabilities by using the production data sets as abscissa, comparing the production data sets with the historical production data sets in the big data to delay data of the delivery cycle, identifying the production data with a fitness lower than 30% as anomaly data, further, sequentially performing a quotient on the number of the N supply chain nodes with the number of the anomaly data identified as anomaly data one by one, thereby obtaining N supply anomaly probabilities based on the N supply chain nodes, and performing a peak deviation anomaly analysis on the N supply anomaly probabilities based on the anomaly delay probabilities of each supply chain node to the delivery cycle, namely, using the production product category as abscissa, constructing a production data graph of the production product supply chain, synchronizing the corresponding delivery time period of the production product to the delivery cycle to the actual delivery time period to the production data, and simultaneously performing a first anomaly positioning on the anomaly node according to the calculated N supply peak deviation probability of the actual delivery cycle, and positioning the anomaly node from the first anomaly node to the first anomaly node.
Further, in order to ensure the accuracy of the N supply anomaly probabilities, it is necessary to collect the historical supply anomaly events existing in the N supply chain nodes through the production supply chain nodes corresponding to the anomaly production data, and analyze the anomaly handling capability of the historical supply anomaly events, that is, obtain N historical anomaly recovery indexes corresponding to the N supply chain link points according to the processing speed of the supply anomaly events occurring in the historical period, where the faster the processing speed is, the higher the corresponding historical anomaly recovery indexes are, and the historical anomaly recovery indexes represent the emergency recovery capability of the supply chain nodes when the anomaly events occur, and finally, the adaptability of the N supply anomaly probabilities in the production process can be adjusted according to the N historical anomaly recovery indexes, that is, the normalized anomaly recovery indexes are used as the coefficient of the anomaly probability to adjust, so as to implement the collaborative management and tamping foundation for the supply chain of digital production.
Step A400: taking the abnormal probability difference between the abnormal probability of the first abnormal node and the expected abnormal probability as an equalization target, and taking the first abnormal node as a Nash equalization node to input a cooperative equalization control model trained in advance;
step A410: after the N supply abnormality probabilities are adjusted, the supply abnormality probability of the supply chain node before the first abnormality node is identified;
step a420: identifying a supply anomaly probability for a supply chain node subsequent to the first anomaly node;
step a430: and carrying out average value calculation according to the supply abnormality probability of the previous supply chain node and the supply abnormality probability of the next supply chain node, and determining the expected abnormality probability.
In the present application, in order to perform collaborative control on a supply chain more accurately, the anomaly probability and the expected anomaly probability of the first anomaly node obtained by the positioning are used as equalization targets, the expected anomaly probability is obtained by adjusting N supply anomaly probabilities, and then the supply anomaly probability of the previous supply chain node of the first anomaly node is identified as the previous anomaly probability, the supply anomaly probability of the next supply chain node of the first anomaly node is identified as the next anomaly probability, further, the average value is obtained by adding and then taking the average value obtained by calculating the supply anomaly probability of the previous supply chain node and the supply anomaly probability of the next supply chain node as the expected anomaly probability, further, equalization calculation is performed in a collaborative equalization control model which takes the anomaly probability of the first anomaly node as a nash equalization node, and the nash equalization control node is used for performing collaborative equalization control on the anomaly probability of the first anomaly node and the expected anomaly probability in advance, and the first anomaly probability is defined as a best equalization anomaly probability when the first anomaly probability of the first anomaly node and the expected anomaly probability are determined.
Meanwhile, the construction flow of the collaborative equalization control model can be as follows:
constructing a collaborative equalization control model, and training the Nash equalization control model after combining the abnormal probability of the Nth abnormal node with the expected abnormal probability in the Nash equalization nodes by utilizing the abnormal probability of the first abnormal node, wherein each node of each layer of the collaborative equalization control model is all connected with the nodes of the upper layer and the lower layer, the collaborative equalization control model comprises an input node, nash equalization nodes and an output node, the input node is a level for data input, the Nash equalization nodes are used for better Nash equalization combination, the output node is a level for result output, the collaborative equalization control model is obtained through training of a training data set and a supervision data set, and the supervision data set is supervision data corresponding to the training data set one by one.
Further, each group of training data in the training data set is input into the collaborative balance management and control model, the output supervision adjustment of the collaborative balance management and control model is carried out through the supervision data corresponding to the group of training data, when the output result of the collaborative balance management and control model is consistent with the supervision data, the current group training is finished, all the training data in the training data set are trained, and the collaborative balance management and control model training is finished.
In order to ensure the convergence and accuracy of the collaborative balance control model, the convergence process may be that when the output data in the collaborative balance control model is converged to one point, the convergence is performed when a certain value is close, the accuracy of the collaborative balance control model may be tested through a test data set, for example, the test accuracy may be set to 80%, and when the test accuracy of the test data set meets 80%, the collaborative balance control model is constructed, so that a limiting effect on collaborative control of a supply chain of digital production is achieved.
Step A500: and carrying out collaborative balance identification on the N supply chain nodes by adopting the collaborative balance management and control model to obtain N balance decision results based on one-to-one correspondence of the N supply chain nodes.
Further, step a500 of the present application further includes:
step A510: generating N alternative strategy sets based on the N supply chain nodes respectively, wherein each supply chain node corresponds to one alternative strategy set;
step A520: determining a first anomaly policy combinationThe first abnormality policy combination ++>For the set of N alternative policy sets, and (2)>；
Step a530: determining a second abnormal strategy combination according to the first abnormal strategy combinationThe second abnormality policy combination +.>For combining +.based on the first anomaly policy>Is not provided with a combination of strategies,
，/>is [1, N]Positive integer in>Is a first abnormal node;
step a540: and performing cost function calculation on the N supply chain nodes based on the first abnormal strategy combination and the second abnormal strategy combination to obtain N balanced decision results based on one-to-one correspondence of the N supply chain nodes.
Further, step a540 of the present application includes:
step a541: acquiring an abnormal probability difference by using the abnormal probability and expected abnormal probability of the first abnormal node, and generating a strategy set based on the first abnormal node by using the minimized abnormal probability difference as an equalization target;
the policy set of the first abnormal node belongs to the first abnormal policy combination, and cost calculation is performed on the policy set of the first abnormal node according to the cost function, so that N balanced decision results based on N supply chain nodes in one-to-one correspondence are obtained.
In the present application, performing collaborative balance identification on N supply chain nodes by using the collaborative balance management and control model constructed as described above means that N selectable policy sets are generated based on the scalable production data in the production data sets included in the N supply chain nodes, and each supply chain node corresponds to one selectable policy set, where the selectable policy set includes collaborative policies under abnormal probability, so that given policy combinations are randomly selected from the selectable policy sets to be recorded as first abnormal policy combinationsFirst abnormality policy combination->Of the set of N alternative policy sets, we mark +.>Further, a second abnormality policy combination is determined based on the first abnormality policy combination>Second abnormality policy combination->For combining based on the first abnormality policy +.>Is a policy combination that lacks only a first abnormal policy combination in the set of N alternative policy sets, in order to match the first oneWhen the abnormal strategy combination is adjusted, the second abnormal strategy combination is synchronously adjusted to ensure the balance marked as the whole cooperative control, and the second abnormal strategy combination is marked as +.>， />Is [1, N]Positive integer in>Is the first outlier node.
Finally, on the basis of the first abnormal strategy combination and the second abnormal strategy combination, carrying out cost calculation on the data by using N supply chain nodes as a cost function shown as follows, wherein the cost function has the expression:
；
wherein,for the first exception node->Performing an adjusted cost function, +.>，For the first exception node->After adjustment, a second abnormality policy combination +.>Cost function sum, < ->N is the total number of supply chain nodes;
obtaining the first abnormal node through calculationPerforming an adjusted cost function, wherein +.>Is the first exception policy combination and +.>，/>Is a second abnormal strategy combination and +.>，Is [1, N]Positive integer in>For the first exception node, ++>A policy set representing an alternative to a jth supply chain node of the N supply chain nodes; />Is indicated at->Next j supply link point selection strategy +.>Probability of->For the first exception node->Based on policy set->Creating a lost payment cost.
Further, the abnormal probability of the first abnormal node and the expected abnormal probability are subjected to difference to obtain an abnormal probability difference, meanwhile, the minimized abnormal probability difference is taken as an equalization target, the equalization target is closed according to the abnormal probability difference of the first abnormal node, a strategy set based on the first abnormal node is generated, the strategy set of the first abnormal node belongs to a first abnormal strategy combination, cost calculation is conducted on the strategy set of the first abnormal node according to a cost function, calculation is conducted on the strategy set corresponding to the strategy set of the first abnormal node based on a cost calculation result corresponding to the strategy set of the first abnormal node, N equalization decision results are sequentially obtained, and accordingly N equalization decision results corresponding to the N supply chain nodes one by one are obtained, and are used as reference data when the supply chain of digital production is subjected to collaborative management in the later period.
In summary, the supply chain collaborative management and control method for digital production provided by the embodiment of the application at least comprises the following technical effects, so that reasonable and accurate management and control of nodes in a supply chain are realized, and collaborative management and control efficiency is improved.
Example two
Based on the same inventive concept as the supply chain collaborative management method for digital production in the foregoing embodiments, as shown in fig. 4, the present application provides a supply chain collaborative management system for digital production, the system comprising:
the node determining module 1 is used for acquiring a production supply chain node, wherein the production supply chain node is a full-flow supply chain node for producing a target product;
the data acquisition module 2 is used for acquiring real-time shared data of the production supply chain nodes and acquiring production data sets of N supply chain nodes;
the node anomaly analysis module 3 is configured to perform node anomaly analysis by using the production data set, and locate a first anomaly node and anomaly probabilities of the first anomaly node, where the first anomaly node is a node with the highest anomaly probability among the N supply chain nodes;
the model training module 4 is configured to input the first abnormal node as a nash equalizing node into a collaborative equalizing control model trained in advance by using an abnormal probability difference between the abnormal probability of the first abnormal node and the expected abnormal probability as an equalizing target;
the collaborative balance recognition module 5 is used for performing collaborative balance recognition on the N supply chain nodes by adopting the collaborative balance management and control model to obtain N balance decision results based on one-to-one correspondence of the N supply chain nodes.
Further, the system further comprises:
the strategy set generation module is used for respectively generating N alternative strategy sets based on the N supply chain nodes, and each supply chain link point corresponds to one alternative strategy set;
a first combination determination module for determining a first abnormal policy combinationThe first abnormality policy combination ++>For the set of N alternative policy sets, and (2)>；
A second combination determining module, configured to determine a second abnormal policy combination according to the first abnormal policy combinationThe second abnormality policy combination +.>For combining +.based on the first anomaly policy>Is lack of a policy combination, is left>，/>Is [1, N]Positive integer in>Is a first abnormal node;
the first calculation module is used for calculating cost functions of N supply chain nodes based on the first abnormal strategy combination and the second abnormal strategy combination, and N equalization decision results based on one-to-one correspondence of the N supply chain nodes are obtained.
Further, the system further comprises:
the second calculation module is used for obtaining an abnormal probability difference by taking the abnormal probability and expected abnormal probability of the first abnormal node and generating a strategy set based on the first abnormal node by taking the minimized abnormal probability difference as an equalization target, wherein the strategy set of the first abnormal node belongs to the first abnormal strategy combination, and carrying out cost calculation on the strategy set of the first abnormal node according to the cost function to obtain N equalization decision results corresponding to N supply chain nodes one by one.
Further, the system further comprises:
the identification module is used for carrying out identification according to the production data set to obtain N supply abnormality probabilities based on N supply chain nodes, wherein the supply abnormality probabilities are abnormal delay probabilities representing that each supply chain node is based on a delivery cycle of arrival;
the first anomaly analysis module is used for carrying out peak deviation anomaly analysis on the N supply anomaly probabilities and positioning the first anomaly node.
Further, the system further comprises:
the event collection module is used for collecting historical supply abnormal events of the N supply chain nodes;
the second abnormality analysis module is used for analyzing the historical supply abnormal events and acquiring N historical abnormality recovery indexes corresponding to the N supply chain nodes, wherein the historical abnormality recovery indexes represent emergency recovery capacity of the supply chain nodes when the abnormal events occur;
the first adjusting module is used for adjusting the N supply abnormality probabilities according to the N historical abnormality recovery indexes.
Further, the system further comprises:
the second adjusting module is used for identifying the abnormal supply probability of the supply chain node before the first abnormal node after adjusting the N abnormal supply probabilities;
the identification module is used for identifying the abnormal supply probability of the supply chain node behind the first abnormal node;
and the third calculation module is used for carrying out average value calculation according to the supply abnormality probability of the previous supply chain node and the supply abnormality probability of the next supply chain node, and determining the expected abnormality probability.
From the foregoing detailed description of the supply chain cooperative control method for digital production, those skilled in the art can clearly understand that the supply chain cooperative control system for digital production in this embodiment, for the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the relevant points refer to the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (5)
1. A supply chain collaborative management method for digital production, the method comprising:
acquiring a production supply chain node, wherein the production supply chain link node is a full-flow supply chain node for producing a target product;
collecting real-time shared data of the production supply chain nodes to obtain production data sets of N supply chain nodes;
carrying out node anomaly analysis by using the production data set, and positioning a first anomaly node and anomaly probability of the first anomaly node, wherein the first anomaly node is a node with the highest anomaly probability in the N supply chain nodes;
taking the abnormal probability and expected abnormal probability of the first abnormal node as balance targets, and taking the first abnormal node as a Nash balance node to input a trained collaborative balance management and control model in advance;
carrying out cooperative equalization identification on N supply chain nodes by adopting the cooperative equalization control model to obtain N equalization decision results based on one-to-one correspondence of the N supply chain nodes;
and carrying out cooperative equalization identification on N supply chain nodes by adopting the cooperative equalization control model, wherein the method further comprises the following steps:
generating N alternative strategy sets based on the N supply chain nodes respectively, wherein each supply chain link point corresponds to one alternative strategy set;
determining a first abnormal policy combination σ, which is a set of the N alternative policy sets, σ= (σ) 1 ,……,σ N )；
Determining a second abnormal strategy combination sigma according to the first abnormal strategy combination -i The second anomaly policy combination sigma -i To be a missing policy combination based on the first abnormal policy combination sigma -i ＝(σ 1 ,…,σ i-1 ,σ i+1 …,σ N )；
Performing cost function calculation on N supply chain nodes based on the first abnormal strategy combination and the second abnormal strategy combination to obtain N balanced decision results based on one-to-one correspondence of the N supply chain nodes;
the method further comprises the steps of:
acquiring an abnormal probability difference by using the abnormal probability and expected abnormal probability of the first abnormal node, and generating a strategy set based on the first abnormal node by using the minimized abnormal probability difference as an equalization target;
the strategy set of the first abnormal node belongs to the first abnormal strategy combination, and cost calculation is carried out on the strategy set of the first abnormal node according to the cost function, so that N balanced decision results based on N supply chain nodes in one-to-one correspondence are obtained;
the expression of the cost function is as follows:
wherein G is i (σ) is the adjusted cost function for the first anomaly node i, j= {0, 1..n }, N being the total number of supply chain nodes;
σ j a policy set representing an alternative for the jth supply chain node; sigma (sigma) j [s j ]Expressed in sigma j The jth supply link point selection strategy s j U, u i (S) a payment cost for the first anomaly node i to generate a loss based on the policy set S, S being an element of the policy set S.
2. The method of claim 1, wherein the node anomaly analysis is performed using the production dataset, a first anomaly node is located, and anomaly probabilities for the first anomaly node, the method comprising:
identifying according to the production data set to obtain N supply abnormality probabilities based on N supply chain nodes, wherein the supply abnormality probabilities are abnormal delay probabilities representing that each supply chain node is based on a delivery cycle of arrival;
and carrying out peak deviation anomaly analysis on the N supply anomaly probabilities, and positioning the first anomaly node.
3. The method of claim 1, wherein the method further comprises:
collecting historical supply abnormal events of the N supply chain nodes;
analyzing the historical supply abnormal events to obtain N historical abnormal recovery indexes corresponding to the N supply chain nodes, wherein the historical abnormal recovery indexes represent emergency recovery capacity of the supply chain nodes when the abnormal events occur;
and adjusting N supply abnormality probabilities according to the N historical abnormality recovery indexes.
4. A method as claimed in claim 3, wherein the method further comprises:
after the N supply abnormality probabilities are adjusted, the supply abnormality probability of the supply chain node before the first abnormality node is identified;
identifying a supply anomaly probability for a supply chain node subsequent to the first anomaly node;
and carrying out average value calculation according to the supply abnormality probability of the previous supply chain node and the supply abnormality probability of the next supply chain node, and determining the expected abnormality probability.
5. A supply chain collaborative management and control system for digital production, the system comprising:
the node determining module is used for acquiring production supply chain nodes, and the production supply chain link nodes are full-flow supply chain nodes for producing target products;
the data acquisition module is used for acquiring real-time shared data of the production supply chain nodes and acquiring production data sets of N supply chain nodes;
the node anomaly analysis module is used for carrying out node anomaly analysis by utilizing the production data set and positioning a first anomaly node and the anomaly probability of the first anomaly node, wherein the first anomaly node is the node with the highest anomaly probability in the N supply chain nodes;
the model training module is used for taking the abnormal probability and expected abnormal probability of the first abnormal node as balance targets, and inputting the first abnormal node as a Nash balance node into a cooperative balance management and control model trained in advance;
the collaborative balance recognition module is used for performing collaborative balance recognition on the N supply chain nodes by adopting the collaborative balance management and control model to obtain N balance decision results based on one-to-one correspondence of the N supply chain nodes;
the strategy set generation module is used for respectively generating N alternative strategy sets based on the N supply chain nodes, and each supply chain link point corresponds to one alternative strategy set;
a first combination determination module for determining a first abnormal policy combination σ, the first abnormal policy combination σ being a set of the N alternative policy sets, σ= (σ) 1 ,……,σ N )；
A second combination determining module for determining a second abnormal policy combination sigma according to the first abnormal policy combination -i The second anomaly policy combination sigma -i To be a missing policy combination based on the first abnormal policy combination sigma -i ＝(σ 1 ,…,σ i-1 ,σ i+1 …,σ N )；
The first calculation module is used for calculating cost functions of N supply chain nodes based on the first abnormal strategy combination and the second abnormal strategy combination to obtain N equalization decision results based on one-to-one correspondence of the N supply chain nodes;
the second calculation module is used for acquiring an abnormal probability difference by using the abnormal probability and expected abnormal probability of the first abnormal node, and generating a strategy set based on the first abnormal node by taking the minimized abnormal probability difference as an equalization target;
the strategy set of the first abnormal node belongs to the first abnormal strategy combination, and cost calculation is carried out on the strategy set of the first abnormal node according to the cost function, so that N balanced decision results based on N supply chain nodes in one-to-one correspondence are obtained;
the expression of the cost function is as follows:
wherein G is i (σ) is the adjusted cost function for the first outlier i, j= {0, 1..n }, N being the supplyThe total number of chain nodes;
σ j a policy set representing an alternative for the jth supply chain node; sigma (sigma) j [s j ]Expressed in sigma j The jth supply link point selection strategy s j U, u i (S) a payment cost for the first anomaly node i to generate a loss based on the policy set S, S being an element of the policy set S.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311571719.6A CN117273422B (en) | 2023-11-23 | 2023-11-23 | Supply chain cooperative control method and system for digital production |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311571719.6A CN117273422B (en) | 2023-11-23 | 2023-11-23 | Supply chain cooperative control method and system for digital production |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117273422A CN117273422A (en) | 2023-12-22 |
| CN117273422B true CN117273422B (en) | 2024-03-15 |
Family
ID=89210944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311571719.6A Active CN117273422B (en) | 2023-11-23 | 2023-11-23 | Supply chain cooperative control method and system for digital production |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117273422B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118313736A (en) * | 2024-06-07 | 2024-07-09 | 张家港大裕橡胶制品有限公司 | Composite production line processing management method and system for rubber glove production |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11037173B1 (en) * | 2019-12-13 | 2021-06-15 | Sift Science, Inc. | Systems and methods for anomaly detection in automated workflow event decisions in a machine learning-based digital threat mitigation platform |
| CN115587295A (en) * | 2021-06-22 | 2023-01-10 | 国网上海市电力公司 | Intelligent generation method and system of supply chain strategy based on machine self-learning |
| CN115796372A (en) * | 2022-12-05 | 2023-03-14 | 江苏阿福科技小额贷款股份有限公司 | Supply chain management optimization method and system based on SCOR |
| CN116308679A (en) * | 2023-04-06 | 2023-06-23 | 上海东普信息科技有限公司 | Supply chain abnormal order processing method, device, equipment and storage medium |
| CN116362526A (en) * | 2023-06-01 | 2023-06-30 | 广州健新科技有限责任公司 | Cloud edge cooperative resource management and control method and system for digital power plant |
| CN117094435A (en) * | 2023-08-17 | 2023-11-21 | 贵州大学 | Novel cloud manufacturing self-adaptive robust service combination and optimization selection method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114612235B (en) * | 2022-03-09 | 2023-03-10 | 烟台大学 | Block chain abnormal behavior detection method based on graph embedding |
-
2023
- 2023-11-23 CN CN202311571719.6A patent/CN117273422B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11037173B1 (en) * | 2019-12-13 | 2021-06-15 | Sift Science, Inc. | Systems and methods for anomaly detection in automated workflow event decisions in a machine learning-based digital threat mitigation platform |
| CN115587295A (en) * | 2021-06-22 | 2023-01-10 | 国网上海市电力公司 | Intelligent generation method and system of supply chain strategy based on machine self-learning |
| CN115796372A (en) * | 2022-12-05 | 2023-03-14 | 江苏阿福科技小额贷款股份有限公司 | Supply chain management optimization method and system based on SCOR |
| CN116308679A (en) * | 2023-04-06 | 2023-06-23 | 上海东普信息科技有限公司 | Supply chain abnormal order processing method, device, equipment and storage medium |
| CN116362526A (en) * | 2023-06-01 | 2023-06-30 | 广州健新科技有限责任公司 | Cloud edge cooperative resource management and control method and system for digital power plant |
| CN117094435A (en) * | 2023-08-17 | 2023-11-21 | 贵州大学 | Novel cloud manufacturing self-adaptive robust service combination and optimization selection method |
Non-Patent Citations (1)
| Title |
|---|
| 基于贝叶斯网络的柔性生产线质量诊断模型;马淑梅 等;机械设计与研究;第28卷(第06期);第107-110页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117273422A (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111337768B (en) | Deep parallel fault diagnosis method and system for dissolved gas in transformer oil | |
| CN107220734A (en) | CNC Lathe Turning process Energy Consumption Prediction System based on decision tree | |
| CN111680820B (en) | Distributed photovoltaic power station fault diagnosis method and device | |
| CN117273422B (en) | Supply chain cooperative control method and system for digital production | |
| CN110222991B (en) | Metering device fault diagnosis method based on RF-GBDT | |
| CN107392304A (en) | A kind of Wind turbines disorder data recognition method and device | |
| CN111445010B (en) | Distribution network voltage trend early warning method based on evidence theory fusion quantum network | |
| CN112818604A (en) | Wind turbine generator risk degree assessment method based on wind power prediction | |
| CN106548270A (en) | A kind of photovoltaic plant power anomalous data identification method and device | |
| CN108090628A (en) | A kind of grain feelings security detection and analysis method based on PSO-LSSVM algorithms | |
| CN112330050A (en) | Power system load prediction method considering multiple features based on double-layer XGboost | |
| CN110516813A (en) | A method of batteries of electric automobile RDR prediction is carried out based on big data machine learning | |
| CN114169445A (en) | Day-ahead photovoltaic power prediction method, device and system based on CAE and GAN hybrid network | |
| CN114997745B (en) | Photovoltaic fault diagnosis tracing method based on depth feature extraction | |
| CN112632840A (en) | Power grid transient stability evaluation method based on adaptive differential evolution algorithm and ELM | |
| CN115358437A (en) | Power supply load prediction method based on convolutional neural network | |
| CN111179576A (en) | Power utilization information acquisition fault diagnosis method and system with inductive learning function | |
| Li et al. | Aero-engine exhaust gas temperature prediction based on LightGBM optimized by improved bat algorithm | |
| Wibawa et al. | Long Short-Term Memory to Predict Unique Visitors of an Electronic Journal | |
| CN117150232B (en) | Large model non-time sequence training data quality evaluation method | |
| Buonanno et al. | Comprehensive method for modeling uncertainties of solar irradiance for PV power generation in smart grids | |
| CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
| CN112633565A (en) | Photovoltaic power aggregation interval prediction method | |
| CN112232570A (en) | Forward active total electric quantity prediction method and device and readable storage medium | |
| CN107977727B (en) | Method for predicting blocking probability of optical cable network based on social development and climate factors |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Supply Chain Collaborative Control Method and System for Digital Production Granted publication date: 20240315 Pledgee: Xi'an innovation financing Company limited by guarantee Pledgor: Xi'an Wisdom Times Information Technology Co.,Ltd. Registration number: Y2024980021913 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |