CN112381113A - HK model-based industrial internet big data collaborative decision-making method - Google Patents
HK model-based industrial internet big data collaborative decision-making method Download PDFInfo
- Publication number
- CN112381113A CN112381113A CN202011113786.XA CN202011113786A CN112381113A CN 112381113 A CN112381113 A CN 112381113A CN 202011113786 A CN202011113786 A CN 202011113786A CN 112381113 A CN112381113 A CN 112381113A
- Authority
- CN
- China
- Prior art keywords
- self
- model
- user
- data
- flexible manufacturing
- 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 35
- 238000004519 manufacturing process Methods 0.000 claims abstract description 83
- 230000003993 interaction Effects 0.000 claims abstract description 10
- 238000013461 design Methods 0.000 claims description 7
- 230000035945 sensitivity Effects 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000013500 data storage Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000013468 resource allocation Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000004088 simulation Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000013467 fragmentation Methods 0.000 description 2
- 238000006062 fragmentation reaction Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000010923 batch production Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000010983 kinetics study Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 235000020004 porter Nutrition 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Algebra (AREA)
- Evolutionary Computation (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an industrial internet big data collaborative decision-making method based on an HK model, which comprises the following steps: designing an industrial internet dynamic collaborative decision flow; carrying out user personalized customization demand self-organizing clustering based on the HK model; carrying out self-organizing clustering on the enterprise flexible manufacturing system based on the noise-containing heterogeneous HK model; and realizing dynamic cooperative decision of flexible manufacturing of enterprises and personalized customization requirements of users by utilizing the dynamic cooperative decision flow of the industrial internet and combining self-organizing clustering results. The method simulates group cooperative intelligence based on local information interaction in the nature and the society, and realizes dynamic cooperative decision of the nature and the society by applying the improved HK model, thereby solving the problems that an enterprise is difficult to independently realize a flexible manufacturing process according to needs in a personalized customization mode due to huge number of nodes, various types and complex and changeable mutual relations in a complex system of an industrial internet, further realizing self-organization and flexible intelligent production of the enterprise workshop, and simultaneously highly matching user requirements.
Description
Technical Field
The invention relates to the technical field of industrial process control, in particular to an industrial internet big data collaborative decision method based on an HK model.
Background
The method is characterized in that an industrial internet platform is created, intelligence plus is expanded, transformation, upgrading and enabling of the manufacturing industry become common knowledge of leaders of various countries, and various pursuit steps such as German, daily, Korean, French and the like are carried out since the first cloud platform Predix (PORTER M E, HEPELMANN J. how small connected products are transferred and matched, Harvard Business Review,2014(11):65-88) is first introduced by the American general electric company in 2015, and various enterprises in China are gradually put into industrial internet construction.
In recent years, new industrial internet modes such as digital management, intelligent production, networking collaboration, personalized customization, service extension and the like are continuously innovated and emerged. While the uniform common products are more and more difficult to meet the individual requirements of users, the individual orders are updated in a large scale, multiple varieties and small batch, and simultaneously, the nodes are large in scale, multiple in variety and complex and changeable in mutual relations due to the fact that the universal interconnection and plug-and-play are carried out under the background of the industrial internet. Therefore, enterprises must break through the traditional supply and demand mode of single channel, mass production and unidirectional flow, realize the seamless butt joint of industrial chain links and highly match the requirements of users. The manual scheduling production mode of the traditional workshop is not suitable any more, the workshop needs to adopt a real-time dynamic scheduling technology, how to accurately grasp the personalized requirements of customers, and the self-organization and flexible intelligent production of the workshop is always a difficult problem which is highly concerned by enterprises.
Human, machine and thing interconnection and intercommunication in industrial internet is a typical large-scale complex system, and the research on the group dynamics of the complex system currently generally uses a method of introducing external input action or external intervention. Such as "leader" (LI Q, XIAL, SONG R Z, et al, leader-follower biological output synchronization on signed two graphs under adaptive Learning Systems,2019,31(10):4185 and 4195) in pilots (leaders-followers), giving certain individuals special rules and information to move the system in the intended way. In recent years, one of the hot research directions for introducing external effects is the containment control of large-scale dynamic networks. In this document (WANG X F, CHEN G R. Pinning control of scale-free dynamic networks. Physica A: Statistical New communications applications,2002,310(3):521-531) in a scaleless network with a connectivity distribution in a power-law form, a holdback control strategy was applied for the first time and a good control effect was achieved. However, the selection of the holddown nodes mostly relates to the global information of a network topology structure, and mainly focuses on a network under a fixed topology, and the holddown control strategy is limited by the number of the holddown nodes, feedback gain, convergence speed and other parameters, so that the flexible manufacturing of enterprises and the dynamic cooperative decision making of large-scale user personalized customization requirements have limitations under the background that the personalized orders are large-scale, multi-variety, small-batch and updated in real time, and simultaneously the nodes are large-scale, various and complex and changeable in interrelations due to the interconnection and plug-and-play of everything under the background of the industrial internet.
Another hotspot study direction for introducing external effects is the opinion kinetics study (SHIRADO H, CHRISTAKIS N A. Locally non-automatic agents improved global human coordination in network experiments. Nature,2017,545(7654):370-374) opinion kinetics model is the process of studying opinion formation, evolution and ultimately consensus in social groups. Generally classified into discrete point of view models and continuous point of view models. For the discrete model, an Sznajd model, a voter model, a Galam election model, and the like are typical. In the continuous view model, the Deffuant model and the HK model based on the bounded trust are representative.
For the evolution problem of continuous view, the HK model is widely applied. The HK model is a model that interacts individual viewpoints with surrounding population viewpoints, thereby promoting the evolution of the viewpoints of the entire population, eventually forming a consistent or dispersed viewpoint. In the text (SU W, CHEN G, HONG Y G. noise leads to square-consensus of Hegselmann-Krause choice dynamics. Automatica.2017,85: 448-. On the basis, the [0,1] interval is generalized to the full space in the text (SU W, GUO J, CHEN X Z, et al. noise-induced synchronization of Hegselmann-Krause dynamics in full space. IEEE Transactions on automatic Control,2019,64(9): 3804-. It is strictly theorized that self-organizing groups of individuals of different traits are grouped together (SU W, GUO J, CHEN X Z, CHEN G, et al. hub fragmentation modification of Hegselmann-Krause-Type dynamics. journal of Franklin Institute,2019,356(16):9867 and 9880).
In order to solve the problem that interaction and cooperation of flexible manufacturing nodes of enterprises and personalized customization requirements of users are difficult, the invention improves a heterogeneous HK model containing noise in a text (Su W, GUO J, CHEN X Z, CHEN G, et al. robust fragmentation modeling of Hegselmann-Krause-Type dynamics. journal of the Franklin Institute,2019,356(16):9867 and 9880), strives to disclose the nature and the inherent rule of a phenomenon hidden on the surface in the complexity of interconnection of human, machine and everything in the industrial internet, realizes independent connection of corresponding flexible manufacturing units of enterprises based on local interaction rules, and provides a new approach for efficient cooperation decision of supply chains and industrial chains in the background of the industrial internet.
Disclosure of Invention
The invention aims to provide an industrial internet big data collaborative decision method based on an HK model, which is used for simulating group collaborative wisdom in nature and society based on local information interaction, and applying the improved HK model to realize dynamic collaborative decision of flexible manufacturing and user personalized customization requirements of enterprises, thereby realizing self-organization and flexible intelligent production of enterprise workshops, being beneficial to changing the traditional supply and demand modes of single channel, batch production and unidirectional flow of enterprises, realizing seamless connection of industrial chain links and highly matching the user requirements; aiming at the defects of the prior art, the invention solves the problems caused by the characteristics of huge number of nodes, various types, complex and changeable interrelations and the like in the industrial internet and realizes the dynamic cooperative decision of the flexible manufacture of the industrial internet and the user requirements.
To solve the above technical problem, an embodiment of the present invention provides the following solutions:
an industrial internet big data collaborative decision-making method based on an HK model comprises the following steps:
s1, designing an industrial internet dynamic collaborative decision flow;
s2, carrying out user personalized customization demand self-organizing clustering based on the HK model;
s3, carrying out self-organizing clustering on the enterprise flexible manufacturing system based on the noise-containing heterogeneous HK model;
s4, realizing the dynamic cooperative decision of enterprise flexible manufacturing and user personalized customization requirements by utilizing the industrial internet dynamic cooperative decision flow and combining the step S2 and the step S3;
s5, transmitting the result of the dynamic collaborative decision to an enterprise manufacturer for big data storage and analysis, matching on a flexible production line, and performing resource allocation and production scheduling according to the matching result;
and S6, monitoring the production process at the cloud.
Further, the step S1 specifically includes:
applying a HK model for user personalized customization requirements to perform self-organizing clustering on user preferences;
substituting the clustering result into an enterprise flexible manufacturing HK model considering the influence of historical data;
and carrying out dynamic cooperative decision making on enterprise flexible manufacturing and large-scale user personalized customization requirements.
Further, the step S2 specifically includes:
let V ═ {1,2, …, n } be the set of n user personalized customization needs, xi(t)∈[0,1]I belongs to V, t is more than or equal to 0 and represents the ith state variable at the moment t, wherein the ith state variable represents the preference of the user;
designing a user personalized customization demand self-organizing clustering rule based on an HK model based on a local interaction rule:
wherein:
Ni(x(t))＝{j∈V:|xi(t)-xj(t)|≤ε1}
Fi(x(t))＝Ni(x(t))-{i}
Ii(x(t))＝{j∈V:|xi(t)-xj(t)|≤ε2}
in the formula: alpha is alphai∈(0,1]Is the inertial strength of the user's preference; n is a radical ofi(x(t))、Ii(x(t))、Fi(x (t)) are neighbor sets corresponding to user requirements i at different thresholds at the time t, wherein | represents the absolute value of the cardinal number or real number of the neighbor sets; epsiloni∈(0,1]A domain threshold representing user preferences; f is the influence degree of the popularity factor and the national situation current on the user preference; beta is aiIs the sensitivity of the epidemic factor, betai∈[0,1]；γiIs the influence of the national conditions.
Further, the step S3 specifically includes:
traditional noisy heterogeneous HK model:
in the formula: s1∪S2＝V，
Is a collection of individuals with heterogeneous bias; j. the design is a square1,J2∈[0,1]Is to satisfy | J1-J2Bias value of | > epsilon; α is the attraction strength of the bias value; i is{·}Whether 1 or 0 is taken according to the condition; { xii(t)}i∈V,t＞0Is independent and uniformly distributed random noise, and has Eξ for delta ≧ 01(1)＝0，
|ξ1(1)|≤δ；
The traditional noise-containing heterogeneous HK model is improved, and comprises the following steps:
removing self flexible manufacturing unit data at the time t from a threshold range, and summing neighbor data at other times t; averaging all historical data stored before the t moment of the user and the real-time data at the t moment, and updating the average into the self data at the t moment; adding the sum of other neighbor data at the time t and the updated self data to calculate an average value, and taking the average value as the self data of the next time;
let V be {1,2, …, n } a set of n enterprise flexible manufacturing units, xi(t)∈[0,1]I belongs to V, t is more than or equal to 0 and represents the ith state variable at the moment t, wherein the manufacturing flexibility is represented;
comprehensively considering real-time data and massive historical data in the flexible manufacturing process, designing a self-organizing clustering rule of an enterprise flexible manufacturing system based on a noise-containing heterogeneous HK model:
wherein:
in the formula: n is a radical ofi(x (t)) is a neighbor set of flexible manufacturing units i within a threshold time t; gi(t) is the sum of all neighbor data within the threshold of flexible manufacturing unit i and all data under the influence of historical data of unit i before time t, where all neighbor data within the threshold of flexible manufacturing unit i is not included inAnd (4) body data.
Further, the step S4 specifically includes:
self-organizing clustering is carried out on the user requirement preference through the self-organizing clustering rule in the step S2;
using the user requirement preference self-organization clustering result in the evolution rule designed in the step S3 to replace the tendency value J1、J2；
In the formula, JmThe cluster is a cluster after self-organizing clustering aiming at large-scale personalized customization user demand preference in industrial internet scene, the number of clustering clusters is dynamic and uncertain, Jm＝{J1,J2,J3,...}。
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
in the design of the user personalized customized demand self-organizing clustering method based on the HK model, on the basis of a traditional viewpoint dynamics HK model, the influence of user preference inertia, fashion factor influence degree and national situation emergent factors is considered, the method is close to reality, a large-scale user demand change process under an industrial internet scene is simulated, an improved user demand HK dynamics evolution model is designed based on a local interaction rule, and therefore the user demand self-organizing clustering can be achieved without depending on preset global information.
In the embodiment of the invention, on the basis of a noise-containing heterogeneous HK model, the influence of historical big data in a flexible manufacturing process is considered in the design of an enterprise flexible manufacturing system self-organizing clustering method based on the noise-containing heterogeneous HK model, group cooperative intelligence based on local information interaction in the nature and the society is simulated, and an improved noise-containing flexible manufacturing HK dynamic evolution model is designed. By applying proper random vibration to the containment units to guide system synchronization, the manufacturing units with different characteristics realize self-organizing clustering according to the tendency values, thereby revealing the nature and the inherent law of the phenomenon hidden on the surface.
In the design of the HK model-based industrial internet dynamic cooperative decision method, according to the evolution rule of a heterogeneous HK model containing random noise, the embodiment of the invention can enable groups with different innate tendencies to spontaneously emerge and cluster according to the tendency value under the drive of random noise with certain intensity, and designs a flexible manufacturing and user demand dynamic cooperative decision model. The method avoids the limitation that the traditional cooperative decision method usually depends on preset global information, and is beneficial to realizing the flexible manufacturing process by enterprises in an industrial internet complex large-scale system according to the independent cooperation of actual user requirements.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be 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 a flow chart of an industrial Internet big data collaborative decision method based on an HK model according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a process of collaborative dynamic decision-making according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a self-organizing clustering process without noise based on a flexible manufacturing HK model in an embodiment of the invention;
FIG. 4 is a schematic diagram of a self-organizing clustering process of applying random noise with certain intensity based on a flexible manufacturing HK model in an embodiment of the present invention;
FIG. 5 is a schematic diagram of a self-organizing clustering process without noise after increasing simulation time based on a flexible manufacturing HK model in the embodiment of the invention;
FIG. 6 is a schematic diagram of a self-organizing clustering process in which random noise with a certain intensity is applied after simulation time is increased based on a flexible manufacturing HK model in an embodiment of the present invention;
fig. 7a to 7c are schematic diagrams of self-organizing clustering results, flexible manufacturing and user requirement cooperative decision results, and noise-free cooperative decision results when the number of the user personalized customization requirements is 50 in the embodiment of the present invention, respectively;
fig. 8a to 8c are schematic diagrams of self-organizing clustering results, flexible manufacturing and user requirement cooperative decision results, and noise-free cooperative decision results, respectively, when the user personalized customization requirements are 60 in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
The embodiment of the invention provides an industrial internet big data collaborative decision-making method based on an HK model, as shown in FIGS. 1-2, the method comprises the following steps:
s1, designing an industrial internet dynamic collaborative decision flow;
s2, carrying out user personalized customization demand self-organizing clustering based on the HK model;
s3, carrying out self-organizing clustering on the enterprise flexible manufacturing system based on the noise-containing heterogeneous HK model;
s4, realizing the dynamic cooperative decision of enterprise flexible manufacturing and user personalized customization requirements by utilizing the industrial internet dynamic cooperative decision flow and combining the step S2 and the step S3;
s5, transmitting the result of the dynamic collaborative decision to an enterprise manufacturer for big data storage and analysis, matching on a flexible production line, and performing resource allocation and production scheduling according to the matching result;
and S6, monitoring the production process at the cloud.
In the embodiment of the invention, the improved HK model is applied to realize the dynamic cooperative decision of the flexible manufacturing nodes of the enterprise and the personalized customization requirements of the user, further realize the self-organization and flexible intelligent production of workshops of the enterprise, finally realize the production and the manufacture of small batches and multiple batches in an all-around way at low cost and high efficiency of the enterprise, and meet the capability of the diversified, fragmented and personalized consumption requirements of the user.
Further, the step S1 specifically includes:
applying a HK model for user personalized customization requirements to perform self-organizing clustering on user preferences;
substituting the clustering result into an enterprise flexible manufacturing HK model considering the influence of historical data;
and carrying out dynamic cooperative decision making on enterprise flexible manufacturing and large-scale user personalized customization requirements.
The industrial internet is interconnected with everything and is plug-and-play, and the user requirements are personalized and diversified, so that the system is large in number of nodes, various in types and complex and changeable in relation, and is a typical large-scale complex system.
The user personalized customization requirement relates to the problem of dynamic change of human viewpoints, inevitably needs a knowledge process of large-scale user viewpoint evolution, and therefore an effective method based on local rules needs to be established.
The method simulates the group cooperative intelligence based on local information interaction in the nature and the society, considers the influence of user preference inertia, the influence degree of epidemic factors and national situation emergency factors on the basis of the traditional viewpoint dynamics HK model, and can effectively disclose the essence and the inherent rule of the phenomenon hidden on the surface.
The step S2 specifically includes:
let V ═ {1,2, …, n } be the set of n user personalized customization needs, xi(t)∈[0,1]I belongs to V, t is more than or equal to 0 and represents the ith state variable at the moment t, wherein the ith state variable represents the preference of the user;
designing a user personalized customization demand self-organizing clustering rule based on an HK model based on a local interaction rule:
wherein:
Ni(x(t))＝{j∈V:|xi(t)-xj(t)|≤ε1}
Fi(x(t))＝Ni(x(t))-{i}
Ii(x(t))＝{j∈V:|xi(t)-xj(t)|≤ε2}
in the formula: alpha is alphai∈(0,1]Is the inertial strength of the user's preference; n is a radical ofi(x(t))、Ii(x(t))、Fi(x (t)) are neighbor sets corresponding to user requirements i at different thresholds at the time t, wherein | represents the absolute value of the cardinal number or real number of the neighbor sets; epsiloni∈(0,1]A domain threshold representing user preferences; f is the influence degree of the popularity factor and the national situation current on the user preference; beta is aiIs the sensitivity of the epidemic factor, betai∈[0,1]；γiIs the influence of the national conditions.
For the application scenario of the industrial internet complex system, the big data in the enterprise flexible manufacturing system not only contains large-scale real-time data, but also comprises massive historical data. For example, after a product is updated, the influence of historical big data needs to be considered for the inheritance capability, compatibility capability and the like of useful characteristics of an old product. Therefore, there is a need for improvement of the conventional noisy heterogeneous bias HK model.
The step S3 specifically includes:
traditional noisy heterogeneous HK model:
in the formula: s1∪S2＝V，
Is a collection of individuals with heterogeneous bias; j. the design is a square1,J2∈[0,1]Is to satisfy | J1-J2Bias value of | > epsilon; α is the attraction strength of the bias value; i is{·}Whether 1 or 0 is taken according to the condition; { xii(t)}i∈V,t＞0Is independent and uniformly distributed random noise, and has Eξ for delta ≧ 01(1)＝0，
|ξ1(1)|≤δ；
The traditional noise-containing heterogeneous HK model is improved, and comprises the following steps:
removing self flexible manufacturing unit data at the time t from a threshold range, and summing neighbor data at other times t; averaging all historical data stored before the t moment of the user and the real-time data at the t moment, and updating the average into the self data at the t moment; adding the sum of other neighbor data at the time t and the updated self data to calculate an average value, and taking the average value as the self data of the next time;
let V be {1,2, …, n } a set of n enterprise flexible manufacturing units, xi(t)∈[0,1]I belongs to V, t is more than or equal to 0 and represents the ith state variable at the moment t, wherein the manufacturing flexibility is represented;
comprehensively considering real-time data and massive historical data in the flexible manufacturing process, designing a self-organizing clustering rule of an enterprise flexible manufacturing system based on a noise-containing heterogeneous HK model:
wherein:
in the formula: n is a radical ofi(x (t)) is a neighbor set of flexible manufacturing units i within a threshold time t; gi(t) is the sum of all neighbor data within the flexible manufacturing unit i threshold, where all neighbor data within the flexible manufacturing unit i threshold contains no self data, and data under the influence of all historical data of unit i prior to time t.
According to the evolution rule of a heterogeneous HK model containing random noise, clusters of groups with different innate tendencies can emerge spontaneously according to tendency values under the drive of the random noise.
The step S4 specifically includes:
self-organizing clustering is carried out on the user requirement preference through the self-organizing clustering rule in the step S2;
using the user requirement preference self-organization clustering result in the evolution rule designed in the step S3 to replace the tendency value J1、J2(ii) a Therefore, the aim of dynamic cooperation of enterprise flexible manufacturing and user requirements can be fulfilled according to matching of self-organizing clustering results.
The number of self-organizing clusters of user needs is dynamically uncertain due to real-time updating of large-scale personalized customization user needs. Therefore, on the basis of the self-organizing clustering rule in step S2, an HK model-based industrial internet dynamic collaborative decision rule is designed:
in the formula, JmThe cluster is a cluster after self-organizing clustering aiming at large-scale personalized customization user demand preference in industrial internet scene, the number of clustering clusters is dynamic and uncertain, Jm＝{J1,J2,J3,...}。
In the following, a specific simulation experiment example is given by taking an industrial internet complex system as an application scene.
For step S3, take n to 60, the threshold for the flexible manufacturing system HK model is 0.1, and the tendency value J is1＝0.8，J20.1, the simulation time T is 100. First, a self-organizing clustering process without adding noise is given, and as shown in fig. 3, the system is clustered into 4 clusters. Then random noise with the noise intensity d equal to 0.3 is applied, the system is guided to be quasi-synchronous, and finally the trend value J is reached1、J2Two clusters nearby, implementing self-organizing clustering, as shown in fig. 4. Increasing simulation time to T1000, and keeping other parameters unchangedThe self-organizing clustering results are shown in fig. 5 and 6.
For step S4, the simulation time T is 1000, and the user personalizes the threshold value e of the demand HK model10.1, threshold ε of flexible HK model fabrication by the Enterprise2The noise intensity d of the HK model is 0.05, and the two dynamic cooperative decisions are 0.3. Sensitivity β to the streamline factor in step S2iSet to 0.8, 0.5, 0.2, respectively, with preference for inertial strength αiThe corresponding sensitivities are set to 0.2, 0.5, 0.8, respectively. When the user personalized customization needs are 50, the self-organizing clustering result is shown in fig. 7a, the flexible manufacturing and user need collaborative decision result is shown in fig. 7b, and the noise-free collaborative decision result is shown in fig. 7 c. When the personalized customization requirements of the user are increased to 60 types, other parameters are not changed, and corresponding simulation results are respectively shown in fig. 8a, fig. 8b and fig. 8 c.
The embodiment of the invention takes an industrial internet large-scale complex system as an application scene, applies the improved HK dynamic evolution model to the dynamic cooperative decision of enterprise flexible manufacturing and large-scale user personalized customization, brings new opportunities for theoretical development, and has wide application prospects. The method can be applied to industrial internet scenes, and can also be popularized to multi-agent and large-scale complex systems or complex networks such as unmanned aerial vehicle formation, intelligent transportation, cloud robots, block chains and the like.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (5)
1. An industrial internet big data collaborative decision-making method based on an HK model is characterized by comprising the following steps:
s1, designing an industrial internet dynamic collaborative decision flow;
s2, carrying out user personalized customization demand self-organizing clustering based on the HK model;
s3, carrying out self-organizing clustering on the enterprise flexible manufacturing system based on the noise-containing heterogeneous HK model;
s4, realizing the dynamic cooperative decision of enterprise flexible manufacturing and user personalized customization requirements by utilizing the industrial internet dynamic cooperative decision flow and combining the step S2 and the step S3;
s5, transmitting the result of the dynamic collaborative decision to an enterprise manufacturer for big data storage and analysis, matching on a flexible production line, and performing resource allocation and production scheduling according to the matching result;
and S6, monitoring the production process at the cloud.
2. The industrial internet big data collaborative decision-making method according to claim 1, wherein the step S1 specifically includes:
applying a HK model for user personalized customization requirements to perform self-organizing clustering on user preferences;
substituting the clustering result into an enterprise flexible manufacturing HK model considering the influence of historical data;
and carrying out dynamic cooperative decision making on enterprise flexible manufacturing and large-scale user personalized customization requirements.
3. The industrial internet big data collaborative decision-making method according to claim 1, wherein the step S2 specifically includes:
let V ═ {1,2, …, n } be the set of n user personalized customization needs, xi(t)∈[0,1]I belongs to V, t is more than or equal to 0 and represents the ith state variable at the moment t, wherein the ith state variable represents the preference of the user;
designing a user personalized customization demand self-organizing clustering rule based on an HK model based on a local interaction rule:
wherein:
Ni(x(t))＝{j∈V:|xi(t)-xj(t)|≤ε1}
Fi(x(t))＝Ni(x(t))-{i}
Ii(x(t))＝{j∈V:|xi(t)-xj(t)|≤ε2}
in the formula: alpha is alphai∈(0,1]Is the inertial strength of the user's preference; n is a radical ofi(x(t))、Ii(x(t))、Fi(x (t)) are neighbor sets corresponding to user requirements i at different thresholds at the time t, wherein | represents the absolute value of the cardinal number or real number of the neighbor sets; epsiloni∈(0,1]A domain threshold representing user preferences; f is the influence degree of the popularity factor and the national situation current on the user preference; beta is aiIs the sensitivity of the epidemic factor, betai∈[0,1]；γiIs the influence of the national conditions.
4. The industrial internet big data collaborative decision-making method according to claim 3, wherein the step S3 specifically includes:
traditional noisy heterogeneous HK model:
in the formula: s1∪S2＝V，
Is a collection of individuals with heterogeneous bias; j. the design is a square1,J2∈[0,1]Is to satisfy | J1-J2Bias value of | > epsilon; α is the attraction strength of the bias value; i is{·}Whether 1 or 0 is taken according to the condition; { xii(t)}i∈V,t＞0Is random noise which is independently and uniformly distributed,and E xi for delta is more than or equal to 01(1)＝0，
|ξ1(1)|≤δ；
The traditional noise-containing heterogeneous HK model is improved, and comprises the following steps:
removing self flexible manufacturing unit data at the time t from a threshold range, and summing neighbor data at other times t; averaging all historical data stored before the t moment of the user and the real-time data at the t moment, and updating the average into the self data at the t moment; adding the sum of other neighbor data at the time t and the updated self data to calculate an average value, and taking the average value as the self data of the next time;
let V be {1,2, …, n } a set of n enterprise flexible manufacturing units, xi(t)∈[0,1]I belongs to V, t is more than or equal to 0 and represents the ith state variable at the moment t, wherein the manufacturing flexibility is represented;
comprehensively considering real-time data and massive historical data in the flexible manufacturing process, designing a self-organizing clustering rule of an enterprise flexible manufacturing system based on a noise-containing heterogeneous HK model:
wherein:
in the formula: n is a radical ofi(x (t)) is a neighbor set of flexible manufacturing units i within a threshold time t; gi(t) is the sum of all neighbor data within the flexible manufacturing unit i threshold, where all neighbor data within the flexible manufacturing unit i threshold contains no self data, and data under the influence of all historical data of unit i prior to time t.
5. The industrial internet big data collaborative decision-making method according to claim 4, wherein the step S4 specifically includes:
self-organizing clustering is carried out on the user requirement preference through the self-organizing clustering rule in the step S2;
using the user requirement preference self-organization clustering result in the evolution rule designed in the step S3 to replace the tendency value J1、J2；
In the formula, JmThe cluster is a cluster after self-organizing clustering aiming at large-scale personalized customization user demand preference in industrial internet scene, the number of clustering clusters is dynamic and uncertain, Jm＝{J1,J2,J3,...}。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011113786.XA CN112381113B (en) | 2020-10-17 | 2020-10-17 | Industrial Internet big data collaborative decision-making method based on HK model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011113786.XA CN112381113B (en) | 2020-10-17 | 2020-10-17 | Industrial Internet big data collaborative decision-making method based on HK model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112381113A true CN112381113A (en) | 2021-02-19 |
| CN112381113B CN112381113B (en) | 2024-02-13 |
Family
ID=74580048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011113786.XA Active CN112381113B (en) | 2020-10-17 | 2020-10-17 | Industrial Internet big data collaborative decision-making method based on HK model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112381113B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113792787A (en) * | 2021-09-14 | 2021-12-14 | 江苏速度遥感大数据研究院有限公司 | Remote sensing big data processing method and system |
| CN113836781A (en) * | 2021-05-31 | 2021-12-24 | 北京科技大学 | Large-scale robot crowd intelligent cooperative decision-making method oriented to personalized customization mode |
| CN113987261A (en) * | 2021-11-08 | 2022-01-28 | 烟台大学 | Video recommendation method and system based on dynamic trust perception |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105511430A (en) * | 2015-12-02 | 2016-04-20 | 西安交通大学 | Socialization and personalized manufacturing environment-oriented CPSS system |
| CN108388977A (en) * | 2018-01-18 | 2018-08-10 | 同济大学 | A kind of co-development system and method towards intelligence manufacture |
| CN109857939A (en) * | 2019-02-01 | 2019-06-07 | 北京航空航天大学 | Accurate method for pushing towards intelligence manufacture service |
| US20200249663A1 (en) * | 2017-10-17 | 2020-08-06 | Guangdong University Of Technology | Method and system for quick customized-design of intelligent workshop |
| CN111582830A (en) * | 2020-05-11 | 2020-08-25 | 浙江师范大学 | Outsource processing service tracking and decision-making method |
-
2020
- 2020-10-17 CN CN202011113786.XA patent/CN112381113B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105511430A (en) * | 2015-12-02 | 2016-04-20 | 西安交通大学 | Socialization and personalized manufacturing environment-oriented CPSS system |
| US20200249663A1 (en) * | 2017-10-17 | 2020-08-06 | Guangdong University Of Technology | Method and system for quick customized-design of intelligent workshop |
| CN108388977A (en) * | 2018-01-18 | 2018-08-10 | 同济大学 | A kind of co-development system and method towards intelligence manufacture |
| CN109857939A (en) * | 2019-02-01 | 2019-06-07 | 北京航空航天大学 | Accurate method for pushing towards intelligence manufacture service |
| CN111582830A (en) * | 2020-05-11 | 2020-08-25 | 浙江师范大学 | Outsource processing service tracking and decision-making method |
Non-Patent Citations (5)
| Title |
|---|
| LIJUN WANG 等: "Swarm Intelligent Cooperative Decision-Making of Large-scale Robots for Individual Customization Mode", 《2021 CHINA AUTOMATION CONGRESS》, pages 264 - 269 * |
| WEI SU 等: "Robust Fragmentation Modeling of Hegselmann-Krause-Type Dynamics", 《ARXIV》, pages 1 - 13 * |
| 张卫;冷建兴;张广博;唐任仲;方水良;: "基于自组织映射网络的制造服务模块动态创建方法", 《计算机集成制造系统》, vol. 23, no. 08, pages 1765 - 1773 * |
| 权锡鉴;杜元伟;: ""互联网+"下大规模个性化定制产品的三元证据融合配置方法", 《科技进步与对策》, vol. 33, no. 21, pages 83 - 89 * |
| 江平宇;杨茂林;李卫东;刘加军;郭威;李普林;: "集体智慧研究综述及其社群化制造应用探索", 《中国机械工程》, vol. 31, no. 15, pages 1852 - 1865 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836781A (en) * | 2021-05-31 | 2021-12-24 | 北京科技大学 | Large-scale robot crowd intelligent cooperative decision-making method oriented to personalized customization mode |
| CN113836781B (en) * | 2021-05-31 | 2024-04-26 | 北京科技大学 | Large-scale robot crowd intelligent collaborative decision-making method oriented to personalized customization mode |
| CN113792787A (en) * | 2021-09-14 | 2021-12-14 | 江苏速度遥感大数据研究院有限公司 | Remote sensing big data processing method and system |
| CN113987261A (en) * | 2021-11-08 | 2022-01-28 | 烟台大学 | Video recommendation method and system based on dynamic trust perception |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112381113B (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112381113A (en) | HK model-based industrial internet big data collaborative decision-making method | |
| Ip et al. | Genetic algorithm solution for a risk-based partner selection problem in a virtual enterprise | |
| CN111539793B (en) | Intelligent manufacturing visual service platform oriented to OPM mode | |
| Tan et al. | Analysis and control of networked game dynamics via a microscopic deterministic approach | |
| CN114417417A (en) | Industrial Internet of things privacy protection system and method based on federal learning | |
| CN115686846B (en) | Container cluster online deployment method integrating graph neural network and reinforcement learning in edge calculation | |
| Gupta et al. | On the emerging notion of evolutionary multitasking: A computational analog of cognitive multitasking | |
| CN111626354B (en) | Clustering method applied to Internet of vehicles and based on task dependency | |
| Adu-Kankam et al. | Towards a hybrid model for the diffusion of innovation in energy communities | |
| Xiang | Exploration of the application of artificial intelligence technology in mechatronics technology based on | |
| CN115345306A (en) | Deep neural network scheduling method and scheduler | |
| Albertini | Networking and division of labour–The case of industrial districts in the North–East of Italy | |
| Shen et al. | Dynamic production scheduling modeling and multi-objective optimization for automobile mixed-model production | |
| Ivaschenko et al. | Conditional management technology for multiagent interaction. | |
| Laili et al. | DSAC-configured Differential Evolution for Cloud-Edge-Device Collaborative Task Scheduling | |
| Wang et al. | Research on multi agent manufacturing process optimization method based on QPSO | |
| CN113836781B (en) | Large-scale robot crowd intelligent collaborative decision-making method oriented to personalized customization mode | |
| Wang et al. | Internet based rural economic entrepreneurship based on mobile edge computing and resource allocation | |
| CN112232481A (en) | Graph neural network recommendation method based on multi-channel coding | |
| Guo | Graph Neural Network-Based Coflow Scheduling in Data Center Networks | |
| Li et al. | Machine Learning Based Key Performance Index Prediction Methods in Internet of Industry | |
| CN116738279A (en) | Micro-grid data processing method and system based on federal learning | |
| Guo et al. | Optimization and Feedback of Assembly Experiment Scheduling Based on Digital Twin | |
| Nie et al. | Distributed Asynchronous Optimization of Multiagent Systems: Convergence Analysis and Its Application | |
| CN117539963A (en) | Dynamic analysis method and system for social network data |
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 |