CN113076698A - Dynamic multi-target collaborative optimization method and system based on workshop big data - Google Patents
Dynamic multi-target collaborative optimization method and system based on workshop big data Download PDFInfo
- Publication number
- CN113076698A CN113076698A CN202110425048.7A CN202110425048A CN113076698A CN 113076698 A CN113076698 A CN 113076698A CN 202110425048 A CN202110425048 A CN 202110425048A CN 113076698 A CN113076698 A CN 113076698A
- Authority
- CN
- China
- Prior art keywords
- flow
- information
- collaborative
- optimization
- big data
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 67
- 230000008569 process Effects 0.000 claims abstract description 40
- 239000000463 material Substances 0.000 claims abstract description 36
- 230000008878 coupling Effects 0.000 claims abstract description 21
- 238000010168 coupling process Methods 0.000 claims abstract description 21
- 238000005859 coupling reaction Methods 0.000 claims abstract description 21
- 241000287828 Gallus gallus Species 0.000 claims abstract description 19
- 238000004458 analytical method Methods 0.000 claims abstract description 15
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 244000144992 flock Species 0.000 claims abstract description 13
- 238000000605 extraction Methods 0.000 claims description 19
- 230000007246 mechanism Effects 0.000 claims description 19
- 235000013330 chicken meat Nutrition 0.000 claims description 18
- 239000000126 substance Substances 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000002195 synergetic effect Effects 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 2
- 240000000111 Saccharum officinarum Species 0.000 abstract description 19
- 235000007201 Saccharum officinarum Nutrition 0.000 abstract description 19
- 230000000694 effects Effects 0.000 abstract description 8
- 238000004519 manufacturing process Methods 0.000 description 19
- 235000011389 fruit/vegetable juice Nutrition 0.000 description 15
- 230000008859 change Effects 0.000 description 10
- 238000005265 energy consumption Methods 0.000 description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 7
- 239000002245 particle Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 241000609240 Ambelania acida Species 0.000 description 4
- 239000010905 bagasse Substances 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003204 osmotic effect Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Computer Hardware Design (AREA)
- Manufacturing & Machinery (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
Abstract
The invention relates to the field of optimization control of a sugarcane squeezing process, and relates to a dynamic multi-objective collaborative optimization method based on workshop big data, which comprises the following steps of 1) collecting big data information of a system and extracting flow characteristic information; 2) analyzing the material flow, the energy flow and the information flow one by one to form an information database, wherein the information database comprises state variables and sequence parameters of the flow; 3) taking a single flow parameter target as an optimization target, and performing coupled cooperation analysis with other two different flow parameter systems to determine a coupling variable, an auxiliary variable and a flow-flow cooperation law in an information database; 4) on the basis of realizing system optimization of each flow under the domination effect of sequence parameters, under the constraint of system coupling variables and auxiliary variables, a mixed chicken flock algorithm is adopted to solve an objective function and calculate process parameters of the system.
Description
Technical Field
The invention relates to the field of optimization control of sugarcane squeezing process design, and relates to a dynamic multi-objective collaborative optimization method based on workshop big data.
Background
The sugarcane juice extraction is the first link of the sugar production process, whether the juice extraction process is smooth or not, and whether the extraction rate, the squeezing quantity, the production energy consumption and the like reach the standard or not will influence the smooth operation and the economic benefit of the whole sugar refinery. The process of squeezing and extracting juice is a complex process with multifactorial, multi-constraint, multi-objective, strong coupling, large non-linearity and uncertainty. In the design of a squeezing production system, the method mainly depends on empirical calculation and analysis, the control of the production process focuses more on the local control of a plurality of key process points, some operation set values still depend on experience values of operators, and the operation indexes are maintained in a reasonable range so as to realize balanced feeding and balanced squeezing. Therefore, the adaptability of the process operation parameters such as the conveying link, the permeating water treatment link and the like of each process in the squeezing process is poor due to the change of working conditions such as squeezing quantity, sugar content of cane material, crushing degree and the like, the dynamic short plate effect caused by the production working condition parameters in the running process and the running state change of each process is more prominent, and the production efficiency, the effect, the energy consumption and the like of the device have various problems and contradictions. At present, the squeezing production system of the sugar refinery in China has the disadvantages of low automation degree, high energy consumption, low safety rate, poor stability, poor adaptability to squeezing quantity fluctuation and the like.
How to utilize big data thinking and combine with artificial intelligence technology to dig valuable information from mass data generated in the production process of an intelligent workshop to guide the operation optimization control of the workshop is a problem which needs to be solved urgently in the production process. The sugarcane squeezing process is a dynamic continuous-operation multi-process production system, is abstracted into interaction and mutual influence of material flow, energy flow and information flow, solves the global cooperative optimization method for effectively coordinating all production units in the sugarcane squeezing process, can effectively solve the problems of low general automation degree, high energy consumption, low safety rate, poor stability, poor adaptability to squeezing quantity fluctuation and the like of a squeezing production system of a sugar factory in China, and provides a solution for energy conservation, emission reduction, high quality and high yield of sugar manufacturing enterprises.
Disclosure of Invention
The invention aims to provide a dynamic multi-objective collaborative optimization method based on workshop big data, so that the limitation of the traditional squeezing system on the squeezing and juice extracting effects and efficiency is broken.
In order to achieve the aim, the dynamic multi-objective collaborative optimization method based on workshop big data provided by the invention is applied to an automatic control system aiming at workshop multifactor, multi-constraint, multi-objective, strong coupling and large nonlinearity, parameters of the workshop operation process comprise parameter systems of material flow, energy flow and information flow,
the dynamic multi-objective collaborative optimization method based on the workshop big data comprises the following steps:
1) collecting big data information of a system, and extracting flow characteristic information by combining with workshop big data resources subjected to cleaning, denoising, integration and conversion preprocessing operations;
2) analyzing the material flow, the energy flow and the information flow one by one to form an information database, wherein the information database comprises state variables and sequence parameters of the flow;
3) respectively taking single substance energy flow collaborative association, energy information flow collaborative association and substance information flow collaborative association as optimization targets, analyzing the optimization targets in a coupled cooperation mode with other two different flow parameter systems, and determining a coupled variable, an auxiliary variable and a flow-flow collaborative action law in an information database;
4) on the basis that each stream realizes system optimization under the domination of sequence parameters, global coordination is carried out on the synergistic effect of the streams in the step 3), and under the consistent constraint of system coupling variables and auxiliary variables, a mixed chicken flock algorithm is adopted to solve an objective function, so that the technological parameters of the system are calculated.
Further, the flow characteristic information in step 1) includes factor variables and operation mechanisms of the involved flows.
Further, the mixed chicken flock algorithm process comprises:
1) redefining a fitness formula, and introducing an elite reverse learning mechanism into population individual initialization;
2) introducing a forward and reverse learning mechanism in the updating iteration of the cock subgroups, and introducing a parent guiding mechanism and self-adaptive factors in the updating iteration of the chickens;
3) and introducing a niche mechanism for updating and maintaining an external archive library and ensuring the diversity of the population.
Further, the stream parameter targets are: material energy flow collaborative association, energy information flow collaborative association and material information flow collaborative association.
The invention also acts on an automatic control system of workshop operation through a dynamic multi-objective collaborative optimization system based on workshop big data, and the system comprises:
the system comprises a flow characteristic attribute extraction layer, a flow characteristic attribute extraction layer and a data processing layer, wherein the flow characteristic attribute extraction layer is used for acquiring big data information of the system, and extracting flow characteristic information by combining workshop big data resources subjected to cleaning, denoising, integrating and conversion preprocessing operations, and the characteristic information comprises factor variables and an operation mechanism of related flows;
the subsystem analysis layer is used for analyzing the material flow, the energy flow and the information flow one by one to form an information database, and the information of the database comprises state variables and sequence parameters of the flow;
the local collaborative optimization layer is used for analyzing the coupling collaboration of two different flow systems in the subsystem analysis model by respectively taking single substance energy flow collaborative association, energy information flow collaborative association and substance information flow collaborative association as optimization targets so as to determine coupling variables, auxiliary variables and a flow-flow collaborative action law in a database;
and on the basis that each stream realizes subsystem optimization under the domination of sequence parameters, globally coordinating the synergistic action of a plurality of streams in the local synergistic optimization layer, solving an objective function by adopting a mixed chicken flock algorithm under the consistent constraint of system coupling variables and auxiliary variables, and calculating the process parameters of the system.
Further, the stream parameter targets are: material energy flow collaborative association, energy information flow collaborative association and material information flow collaborative association.
Advantageous effects
The method provided by the invention is used for carrying out overall coordination optimization on a workshop operation system by using a three-stream coordination method of material flow, energy flow and information flow, and constructing a workshop operation process optimization design model based on a flow characteristic attribute extraction method, an entropy analysis method and other methods based on a material flow, energy flow and information flow coordination mechanism in a running big data mining and squeezing process, and provides a coordination solver of a mixed chicken flock method for solving the model. Through the three-flow synergistic effect, the operating parameters of the juice squeezing and extracting process are optimized, the dynamic cooperative control of material flow, energy flow and information flow in the juice squeezing and extracting process is realized, the system is ensured to be in the optimal state under different production boundary conditions, the squeezing efficiency and effect are improved, and the energy consumption is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
FIG. 1 is a "three-stream" coupling relationship analysis diagram of a sugar cane crushing system according to the present invention.
FIG. 2 is a big data driven based dynamic multi-objective collaborative optimization modeling solving diagram according to the invention.
FIG. 3 is a schematic diagram of multi-objective collaborative optimization modeling of a pressing system according to the present invention.
FIG. 4 is a schematic diagram of an optimization solution strategy based on a hybrid chicken flock algorithm according to the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
As shown in figure 1, the invention takes a sugarcane squeezing workshop as an example, the sugarcane squeezing and juice extracting process is a complex process with multiple factors, multiple constraints, multiple targets, strong coupling, large nonlinearity and uncertainty, the three-stream coupling relation in the squeezing workshop divides the sugarcane squeezing process into three subsystems of material flow, energy flow and information flow according to the basic characteristics of substances in a sugarcane squeezing system, the related factors and the flow change relation, and the material flow is a processed main body and comprises sugarcane, permeated water, mixed juice, bagasse and the like; the energy flow is the driving force of the process, and comprises heat energy for heating the permeation water, electric energy for operating the equipment, mechanical energy and the like; the information flow is the sum of the reaction of material flow behavior, energy flow behavior and external environment information and artificial regulation and control information, and comprises bagasse conversion degree, bagasse water content, conveyor belt speed, bagasse flow, osmotic water temperature, process index attribute, efficiency attribute, production boundary attribute, equipment load attribute and the like. By analyzing the coupling relation of the sugarcane squeezing process, the interaction among the material flow, the energy flow and the information flow is primarily analyzed, the material flow restricts the change of the energy flow, such as the change of the sugarcane flow and the change of the equipment energy flow influenced by the flow of the permeating water, and the change of the energy flow influences the conversion efficiency of the material flow, such as the flow of the mixed juice influenced by the energy flow of a squeezer and the flow of the permeating juice/water influenced by the pumping energy flow. The material flow and the energy flow are used as carriers of the information flow to influence the index of the information flow, and the information flow restricts the change of the material flow and the energy flow, for example, the process index in the information flow influences the flow rate of sugarcane and the energy flow of equipment.
As shown in FIGS. 2-3, the dynamic multi-objective collaborative optimization system based on the plant big data divides a sugarcane squeezing system into a material flow subsystem, an energy flow subsystem and an information flow subsystem. According to the three-flow coupling relation in the sugarcane squeezing and juice extracting process, the three-flow collaborative optimization modeling of the sugarcane squeezing and juice extracting system comprises a big data center, a flow characteristic extraction layer, a subsystem analysis layer, a local collaborative optimization layer, a system collaborative optimization layer and a system optimization solution layer.
The big data center is used for collecting historical data and real-time data of state parameters of processed materials, state parameters of energy generated in the squeezing process, state parameters of equipment and the like in the sugarcane squeezing and juice extracting process, and big data information including production plans, raw material components, energy data, equipment states, finished product quality and the like is obtained through data preprocessing.
The flow characteristic extraction layer is used for acquiring big data information of the system, and extracting flow characteristic information comprising factor variables of related flows and an operation mechanism by combining workshop big data resources subjected to preprocessing operations including cleaning, denoising, integration, conversion and the like; the stream feature extraction layer provides reliable and reusable data resources for subsequent multi-level analysis. According to the basic characteristics of the substances in the pressing system and the relation of flow change, the comprehensive application of the large data information of the workshop comprises one or more of the following analysis methods: time progression method, alternating frequency method, experience transformation method, deep learning method, principal component analysis method and other analysis system related factors.
And the subsystem analysis layer is used for analyzing the single flow subsystem by using the flow characteristic attribute extraction layer to form a database of certain information, the information database comprises sequence parameters and state variables playing a dominant role in the flow, and the sequence parameters comprise material flow sequence parameters, energy flow sequence parameters and information flow sequence parameters. Specifically, a system optimization target is used as output, a flow feature extraction layer extracts various state variables as input, the weight of each state parameter is determined based on a data driving model, a multi-attribute decision is made to obtain key factors of system performance, and a state parameter system of each flow subsystem is established;
the local collaborative optimization layer is used for respectively taking material energy flow collaborative association, energy information flow collaborative association and material information flow collaborative association as optimization targets, analyzing the coupling collaboration of two different flow systems in the subsystem analysis layer by combining a database and applying an entropy analysis and mutual information method, and determining auxiliary variables, coupling variables and flow-flow collaborative law related to each target of the database.
The system collaborative optimization layer takes the systematic optimization design of material flow, energy flow and information flow collaboration as an optimization model of the layer, takes cane juice extraction prediction, squeezing quantity prediction, energy consumption prediction and collaborative parameters as optimization targets and takes process gradual change attributes as the optimization targets; and the empirical attribute, the equipment load attribute, the process procedure attribute and the operation tolerance attribute are used as constraint conditions. On the basis that each flow realizes subsystem optimization under the domination effect of sequence parameters, a target set is used as output and auxiliary variables and coupling variables in corresponding flow characteristic attributes are used as input, global coordination is carried out on the mutual cooperation of a plurality of flows between the local cooperative optimization layers on the basis of a depth data driving method, and a squeezing process cooperative optimization model is established.
And a system optimization solving layer, wherein the process parameters of the system are calculated by adopting a mixed chicken flock algorithm pair on the system collaborative optimization layer, and the process parameters act on an automatic control system, so that the system is ensured to be in an optimal state under different production boundary conditions, the squeezing effect and the squeezing amount are improved, and the energy consumption is reduced.
As shown in FIG. 4, the optimization solution strategy diagram based on the hybrid chicken flock algorithm is used for collecting system targets { f1(X),.......,fM(X), and M is the number of the target set and is input into an optimization solving layer, and particles with multiple dimensions are randomly generated, wherein each particle corresponds to the value of a group of operating parameters under the current working condition. And when all the particles are subjected to traversal optimization, inputting each particle into a system process model obtained by the system collaborative optimization layer, and obtaining a real-time system operation target through a depth data driven learning algorithm. The aim of the operation is to reduce the energy consumption while ensuring high extraction and high extraction rates. The specific optimization process is as follows:
1) and setting an evolution algebra of the population, an algebra updated by a level system, a constraint variable range, the capacity of an external file and the proportion of three subgroups, introducing a reverse learning strategy, solving a reverse population for randomly generated particles, and selecting a population with better fitness from the initial population and the reverse population to form an initial population NP. The fitness calculation comprises the following steps:
2) and dividing the whole solution space into three subgroups according to the set parameters and the arrangement sequence of the fitness of the individuals of the initial population, wherein the subgroups are a cock group NR, a hen group NH and a chick group NC, and updating the subgroups according to corresponding updating formulas.
3) The optimal and worst individuals are determined according to the proposed fitness.
4) And (3) introducing a forward and reverse learning mechanism into the cock subgroups, namely, forward learning to the globally optimal individual to accelerate convergence, and when the globally optimal individual is found to be unchanged for multiple times, reversely learning to the globally worst individual to jump out a locally optimal solution with a certain probability.
xt+1 i＝xt i*(1+Randn(0,σ2))+w1(xt best-xt i)
xt+1 i＝xt i*(1+Randn(0,σ2))+w2(xt worst-xt i)
In the formula, Randn (0, sigma)2) Is a mean value of 0 and a standard deviation of σ2Gaussian distribution of (x)t iIs the position, x, in the ith individual at the t iterationt+1 iPosition in the ith individual at t +1 iteration, xt bestFor globally optimal individuals at the t-th iteration, xt bestIs the global worst individual at the t-th iteration, w1And w2Learning factors, f, for forward and backward learning, respectivelyiFitness of the ith individual, fkIs the fitness of the kth individual, k is equal to [1, NH ]]。
5) And updating the formula of the position of the hen subgroup.
xt+1 i＝xt i+S1*rand*(xt r1-xt i)+S2*rand*(xt r2-xt i)
In the formula, xt iIs the position, x, in the ith individual at the t iterationt+1 iPosition in the ith individual at the t +1 th iteration, r1The cock followed by the hen, r2Selecting randomly cock or hen for the whole chicken group, and r1≠r2。
6) Introducing a parent guiding mechanism and an adaptive factor into the position update of the chicken.
xt+1 i＝w*xt i+λ1*(xt m-xt i)+λ2*(xt r1-xt i)
In the formula, xt iIs the position, x, in the ith individual at the t iterationt+1 iPosition in the ith individual at t +1 iteration, xt mIs the hen individual followed by the ith individual,
is a cock individual followed by the chicken. w is the weight, λ1、λ2The factors for learning hen and cock are shown respectively.
7) And storing the obtained non-dominated solution set in an external archive, and updating and maintaining the external archive set by introducing a niche sharing mechanism to ensure the diversity of the population.
8) And (5) reaching the iteration times, finishing traversing optimization, and outputting an external file set. And according to the actual production requirement, making a corresponding optimal solution in an external archive library.
The fusion of the chicken flock algorithm and the forward and reverse learning mechanism can not only process data independently, but also coordinate and act together; the method can ensure the particle development and solution exploration space and jump out of local optimum in time when the algorithm is stopped and premature. The integration of the niche technology ensures the effectiveness of the mixed chicken swarm algorithm in solving the multi-peak function optimization problem.
Example 2
Based on the embodiment 1, a dynamic multi-objective collaborative optimization method based on workshop big data is provided, which includes the steps:
1) historical data and real-time data of state parameters of processed substances, state parameters of energy generated in the squeezing process, state parameters of equipment and the like in the sugarcane squeezing and juice extracting process are collected, and big data information including production plans, raw material components, energy data, equipment states, finished product quality and the like is obtained through data preprocessing. And acquiring big data information of a system, and extracting factor variables of related flows and flow characteristic information of an operation mechanism by combining with workshop big data resources subjected to cleaning, denoising, integrating and conversion preprocessing operations.
2) Analyzing the material flow, the energy flow and the information flow one by one to form an information database, wherein the information database comprises state variables and sequence parameters of the flow; the sequence parameters comprise material flow sequence parameters, energy flow sequence parameters and information flow sequence parameters. Specifically, a system optimization target is used as output, the flow feature extraction layer extracts various state variables as input, the weight of each state parameter is determined based on a data driving model, the key factors of system performance are obtained through multi-attribute decision, and a state parameter system of each flow subsystem is established.
3) Respectively taking single substance energy flow collaborative association, energy information flow collaborative association and substance information flow collaborative association as optimization targets, analyzing the optimization targets in a coupled cooperation mode with other two different flow parameter systems, and determining a coupled variable, an auxiliary variable and a flow-flow collaborative action law in an information database;
4) on the basis that each stream realizes system optimization under the domination of sequence parameters, global coordination is carried out on the synergistic effect of the streams in the step 3), and under the consistent constraint of system coupling variables and auxiliary variables, a mixed chicken flock algorithm is adopted to solve an objective function, so that the technological parameters of the system are calculated.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all modifications and equivalents of the present invention, which are made by the contents of the present specification and the accompanying drawings, or directly/indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (6)
1. A dynamic multi-objective collaborative optimization method based on workshop big data is applied to an automatic control system of workshop operation and is characterized in that parameters of the workshop operation process comprise parameter systems of material flow, energy flow and information flow,
the dynamic multi-objective collaborative optimization method based on the workshop big data comprises the following steps:
1) collecting big data information of a system, and extracting flow characteristic information by combining with workshop big data resources subjected to cleaning, denoising, integration and conversion preprocessing operations;
2) analyzing the material flow, the energy flow and the information flow one by one to form an information database, wherein the information database comprises state variables and sequence parameters of the flow;
3) respectively taking single substance energy flow collaborative association, energy information flow collaborative association and substance information flow collaborative association as optimization targets, analyzing the optimization targets in a coupled cooperation mode with other two different flow parameter systems, and determining a coupled variable, an auxiliary variable and a flow-flow collaborative action law in an information database;
4) on the basis that each stream realizes system optimization under the domination of sequence parameters, global coordination is carried out on the synergistic effect of the streams in the step 3), and under the consistent constraint of system coupling variables and auxiliary variables, a mixed chicken flock algorithm is adopted to solve an objective function, so that the technological parameters of the system are calculated.
2. The method for dynamic multi-objective collaborative optimization based on plant big data according to claim 1, wherein the flow characteristic information in the step 1) comprises factor variables and operation mechanisms of the involved flows.
3. The dynamic multi-objective collaborative optimization method based on workshop big data according to claim 1,
the mixed chicken flock algorithm process comprises the following steps:
1) redefining a fitness formula, and introducing an elite reverse learning mechanism into population individual initialization;
2) introducing a forward and reverse learning mechanism in the updating iteration of the cock subgroups, and introducing a parent guiding mechanism and self-adaptive factors in the updating iteration of the chickens;
3) and introducing a niche mechanism for updating and maintaining an external archive library and ensuring the diversity of the population.
4. The dynamic multi-objective collaborative optimization method based on workshop big data according to claim 1, wherein the flow parameter objectives are: material energy flow collaborative association, energy information flow collaborative association and material information flow collaborative association.
5. The dynamic multi-objective collaborative optimization system based on the workshop big data is used on an automatic control system of workshop operation and is characterized by comprising the following steps:
the system comprises a flow characteristic attribute extraction layer, a flow characteristic attribute extraction layer and a data processing layer, wherein the flow characteristic attribute extraction layer is used for acquiring big data information of the system, and extracting flow characteristic information by combining workshop big data resources subjected to cleaning, denoising, integrating and conversion preprocessing operations, and the characteristic information comprises factor variables and an operation mechanism of related flows;
the subsystem analysis layer is used for analyzing the material flow, the energy flow and the information flow one by one to form an information database, and the information of the database comprises state variables and sequence parameters of the flow;
the local collaborative optimization layer is used for analyzing the coupling collaboration of two different flow systems in the subsystem analysis model by respectively taking single substance energy flow collaborative association, energy information flow collaborative association and substance information flow collaborative association as optimization targets so as to determine coupling variables, auxiliary variables and a flow-flow collaborative action law in a database;
and on the basis that each stream realizes subsystem optimization under the domination of sequence parameters, globally coordinating the synergistic action of a plurality of streams in the local synergistic optimization layer, solving an objective function by adopting a mixed chicken flock algorithm under the consistent constraint of system coupling variables and auxiliary variables, and calculating the process parameters of the system.
6. The dynamic multi-objective collaborative optimization system based on plant big data according to claim 5, wherein the flow parameter objectives are: material energy flow collaborative association, energy information flow collaborative association and material information flow collaborative association.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110425048.7A CN113076698B (en) | 2021-04-20 | 2021-04-20 | Dynamic multi-target collaborative optimization method and system based on workshop big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110425048.7A CN113076698B (en) | 2021-04-20 | 2021-04-20 | Dynamic multi-target collaborative optimization method and system based on workshop big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113076698A true CN113076698A (en) | 2021-07-06 |
| CN113076698B CN113076698B (en) | 2022-05-31 |
Family
ID=76618363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110425048.7A Active CN113076698B (en) | 2021-04-20 | 2021-04-20 | Dynamic multi-target collaborative optimization method and system based on workshop big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113076698B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743652A (en) * | 2021-08-06 | 2021-12-03 | 广西大学 | Sugarcane squeezing process prediction method based on depth feature recognition |
| CN117250931A (en) * | 2023-11-16 | 2023-12-19 | 一夫科技股份有限公司 | Gypsum board production intelligent control method and system based on data fusion |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070253874A1 (en) * | 2001-07-16 | 2007-11-01 | Todd Foret | System, method and apparatus for treating liquids with wave energy from plasma |
| CN101887544A (en) * | 2010-06-10 | 2010-11-17 | 同济大学 | Optimization modeling method for coupling of production and energy of continuous enterprises |
| CN102426663A (en) * | 2011-05-20 | 2012-04-25 | 新奥科技发展有限公司 | Method for controlling universal-energy network by universal-energy current sequence parameter |
| CN103177299A (en) * | 2011-12-26 | 2013-06-26 | 新奥科技发展有限公司 | Method and system for optimizing smart energy network |
| CN104880949A (en) * | 2015-05-27 | 2015-09-02 | 江南大学 | Method of acquiring workpiece-processing optimal scheduling based on improved chicken flock algorithm |
| CN107942686A (en) * | 2017-12-28 | 2018-04-20 | 广西大学 | Clarifying process operating and optimization control method based on depth limit learning machine |
| CN108073755A (en) * | 2017-05-25 | 2018-05-25 | 烟台仙崴机电有限公司 | Electric car switched reluctance motor system multi-objective optimization design of power method |
| CN108107737A (en) * | 2017-12-28 | 2018-06-01 | 广西大学 | The cooperative optimization method of cane juice clarification process based on entropy minimum |
| CN109749977A (en) * | 2019-03-06 | 2019-05-14 | 广西壮族自治区农业科学院 | By-product from sugarcane feed fermenting microbial inoculum and preparation method thereof |
| CN110412960A (en) * | 2019-08-22 | 2019-11-05 | 广东省生物工程研究所（广州甘蔗糖业研究所） | Into squeezing and wisdom production management method and system are squeezed based on the sugar refinery of cloud computing |
| CN111723909A (en) * | 2020-06-15 | 2020-09-29 | 武汉轻工大学 | Optimization method and system of fuzzy neural network model |
-
2021
- 2021-04-20 CN CN202110425048.7A patent/CN113076698B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070253874A1 (en) * | 2001-07-16 | 2007-11-01 | Todd Foret | System, method and apparatus for treating liquids with wave energy from plasma |
| CN101887544A (en) * | 2010-06-10 | 2010-11-17 | 同济大学 | Optimization modeling method for coupling of production and energy of continuous enterprises |
| CN102426663A (en) * | 2011-05-20 | 2012-04-25 | 新奥科技发展有限公司 | Method for controlling universal-energy network by universal-energy current sequence parameter |
| CN103177299A (en) * | 2011-12-26 | 2013-06-26 | 新奥科技发展有限公司 | Method and system for optimizing smart energy network |
| CN104880949A (en) * | 2015-05-27 | 2015-09-02 | 江南大学 | Method of acquiring workpiece-processing optimal scheduling based on improved chicken flock algorithm |
| CN108073755A (en) * | 2017-05-25 | 2018-05-25 | 烟台仙崴机电有限公司 | Electric car switched reluctance motor system multi-objective optimization design of power method |
| CN107942686A (en) * | 2017-12-28 | 2018-04-20 | 广西大学 | Clarifying process operating and optimization control method based on depth limit learning machine |
| CN108107737A (en) * | 2017-12-28 | 2018-06-01 | 广西大学 | The cooperative optimization method of cane juice clarification process based on entropy minimum |
| CN109749977A (en) * | 2019-03-06 | 2019-05-14 | 广西壮族自治区农业科学院 | By-product from sugarcane feed fermenting microbial inoculum and preparation method thereof |
| CN110412960A (en) * | 2019-08-22 | 2019-11-05 | 广东省生物工程研究所（广州甘蔗糖业研究所） | Into squeezing and wisdom production management method and system are squeezed based on the sugar refinery of cloud computing |
| CN111723909A (en) * | 2020-06-15 | 2020-09-29 | 武汉轻工大学 | Optimization method and system of fuzzy neural network model |
Non-Patent Citations (4)
| Title |
|---|
| 张慕雪 等: "一种基于正向学习和反向学习的改进鸡群算法", 《微电子学与计算机》 * |
| 汪淑奇 等: "物质流、能量流与信息流协同的探讨及应用", 《华中科技大学学报(自然科学版)》 * |
| 蒙艳玫 等: "基于数据驱动的煮糖结晶过程自适应控制", 《甘蔗糖业》 * |
| 陈劼 等: "基于多场协同的煮糖设备全局协调优化方法研究", 《装备制造技术》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743652A (en) * | 2021-08-06 | 2021-12-03 | 广西大学 | Sugarcane squeezing process prediction method based on depth feature recognition |
| CN113743652B (en) * | 2021-08-06 | 2022-03-11 | 广西大学 | Sugarcane squeezing process prediction method based on depth feature recognition |
| CN117250931A (en) * | 2023-11-16 | 2023-12-19 | 一夫科技股份有限公司 | Gypsum board production intelligent control method and system based on data fusion |
| CN117250931B (en) * | 2023-11-16 | 2024-01-23 | 一夫科技股份有限公司 | Gypsum board production intelligent control method and system based on data fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113076698B (en) | 2022-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113076698B (en) | Dynamic multi-target collaborative optimization method and system based on workshop big data | |
| CN110472840B (en) | Agricultural water conservancy scheduling method and system based on neural network technology | |
| CN115545321A (en) | On-line prediction method for process quality of silk making workshop | |
| CN105760621B (en) | A kind of assembly line balancing method considering complexity | |
| CN113869571A (en) | Smart energy building comprehensive information physical fusion method based on heterogeneous data | |
| CN110260470A (en) | Central air-conditioning parallel connection cold load optimal distribution method based on colony intelligence framework | |
| CN104318090A (en) | Least square method support vector machine-based generalized prediction method in lysozyme fermentation process | |
| CN113325719B (en) | Distributed pulse consistency control method and system for time-varying time-lag multi-agent | |
| CN109254530A (en) | MFA control method based on grinding process basis circuit | |
| CN106482507B (en) | A kind of cement decomposing furnace combustion automatic control method | |
| Meng et al. | Modeling and optimization of sugarcane juice clarification process | |
| CN107463620A (en) | A kind of elevator accident early-warning and predicting system based on data mining | |
| CN103792845B (en) | A kind of Ferment of DM process mends the method and system of sugared rate optimized control | |
| CN116611478A (en) | Industrial process data enhancement method for generating countermeasure network based on depth threshold | |
| CN112990561A (en) | Industrial industry chain cooperative decision-making method based on workflow model | |
| CN112200391A (en) | Power distribution network edge side load prediction method based on k-nearest neighbor mutual information characteristic simplification | |
| CN108921287A (en) | A kind of optimization method and system of neural network model | |
| CN105511270B (en) | A kind of PID controller parameter optimization method and system based on coevolution | |
| CN111724277A (en) | New energy and multi-element load value matching method and system | |
| Pawlowski et al. | Event-based selective control strategy for raceway reactor: A simulation study | |
| CN116154875A (en) | Photovoltaic power station active power optimization distribution method based on TCN and error function | |
| Kong et al. | A reliable and efficient hybrid PSO for parameters optimization of LS-SVM in production rate prediction | |
| CN112796747B (en) | Oil and gas drilling strategy prediction method and device based on multiple targets | |
| Kaipbergenov et al. | Modeling of the Technological Process of Ammonization of Soda Production Under Conditions of Changing Initial Data | |
| CN115204696B (en) | Aircraft production line assembly operation scheduling method based on ATC and ALC algorithms |
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 |