CN108665094A - A kind of copper plate/strip founding-tandem rolling Optimization Scheduling of data-driven - Google Patents
A kind of copper plate/strip founding-tandem rolling Optimization Scheduling of data-driven Download PDFInfo
- Publication number
- CN108665094A CN108665094A CN201810386951.5A CN201810386951A CN108665094A CN 108665094 A CN108665094 A CN 108665094A CN 201810386951 A CN201810386951 A CN 201810386951A CN 108665094 A CN108665094 A CN 108665094A
- Authority
- CN
- China
- Prior art keywords
- production
- data
- copper plate
- strip
- socket
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 title claims abstract description 46
- 229910052802 copper Inorganic materials 0.000 title claims abstract description 46
- 239000010949 copper Substances 0.000 title claims abstract description 46
- 238000005457 optimization Methods 0.000 title claims abstract description 24
- 238000005096 rolling process Methods 0.000 title claims abstract description 16
- 238000004519 manufacturing process Methods 0.000 claims abstract description 125
- 238000000034 method Methods 0.000 claims abstract description 61
- 241000196324 Embryophyta Species 0.000 claims abstract description 24
- 230000002786 root growth Effects 0.000 claims abstract description 16
- 230000008569 process Effects 0.000 claims abstract description 13
- 230000004927 fusion Effects 0.000 claims abstract description 11
- 230000008447 perception Effects 0.000 claims description 39
- 230000006870 function Effects 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 10
- 230000003252 repetitive effect Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000012010 growth Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000000903 blocking effect Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000007418 data mining Methods 0.000 claims description 3
- 238000013501 data transformation Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000005266 casting Methods 0.000 claims 5
- 239000000463 material Substances 0.000 abstract description 3
- 238000002156 mixing Methods 0.000 abstract 1
- 230000006399 behavior Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 239000002689 soil Substances 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 210000004209 hair Anatomy 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 241000254158 Lampyridae Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000035558 fertility Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—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
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- 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
-
- 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)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- Manufacturing & Machinery (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
One layer of sensor model is established in high-precision copper plate/strip product line；High-precision copper plate/strip production line task demand is formed according to production order, by organically blending to high-precision copper plate/strip physical message, the high-precision copper plate/strip founding tandem rolling whole process job scheduling model to constraints such as product requirements in production consideration equipment capacity, production technology regulation and order is established；Multiobjective Intelligent optimization algorithm of the design based on plant root growth model solves job scheduling model.The present invention provides a kind of fusion Optimal Operation Model and optimization method for high-precision copper plate/strip founding continuous rolling production line, make production demand pairs according to acquisition, equipment state, material tracking, spot dispatch etc. can be accurately controlled integrates autonomy with remote collaboration, high-precision copper plate/strip Product Precision and production built-in unit overall utilization rate are improved, production cost is reduced.
Description
Technical Field
The invention relates to the field of information material fusion optimization scheduling methods in high-precision copper plate strip fusion casting-continuous rolling production, in particular to a data-driven copper plate strip fusion casting-continuous rolling optimization scheduling method.
Background
The copper plate and strip products belong to high-end industrial products, the production process is limited by randomness and uncertainty factors, most orders of the copper plate and strip products have the characteristics of various types, small batch, real-time requirements and the like, and the requirements on the processing flexibility and intelligent scheduling of a copper plate and strip production line are high. Along with the improvement of the equipment level of the copper plate and strip production line, the acquisition of physical process information such as a large amount of production, the real-time state of equipment and the like is simpler and easier. However, the intelligent degree of management and scheduling of the copper strip production enterprise is still not high, and the production line lacks accurate control and remote cooperation comprehensive autonomy from the aspects of data acquisition, equipment state, material tracking, field scheduling and the like, so that the product precision, production cost and efficiency are difficult to reach the standard, and a large amount of manpower, equipment resources and energy are consumed. Therefore, in the production process of copper plate and strip products, a heterogeneous interconnected information physical fusion system structure support penetrating through a bottom layer reliable perception model and an upper layer optimized scheduling method is needed in the face of a large amount of diversified time-varying physical process information.
The information physical fusion scheduling optimization model established aiming at the high-precision copper plate production is a multi-main-body space-time structure which embodies certain complexity and is formed by interactive links or elements, and the scheduling optimization object of the model mostly presents the characteristics of large scale, nonlinearity, multiple targets, multiple stages, large heterogeneous information amount and the like. The traditional dynamic programming algorithm can be oriented to small system models with few dimensions, but is also oriented to the problem of dimension disaster when a multi-objective task is oriented. If a multi-target is converted into a single-target solving strategy, the difference of weight values among targets and mutual acceptability and anisotropy among different targets cannot be eliminated, and results are difficult to compare.
Disclosure of Invention
The invention overcomes the technical defects of the existing planning algorithm and provides a novel data-driven copper plate and strip casting-continuous rolling optimization scheduling method. The invention provides an information physical fusion optimization scheduling model which can solve the scheduling problem caused by the lack of accurate control and remote cooperative comprehensive autonomy of a high-precision copper strip casting-tandem rolling production line, avoid resource idling and service cooperative optimization, and improve the equipment efficiency of the whole production line by using the growth behavior of plant roots.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a data-driven copper plate and strip casting-continuous rolling optimization scheduling method comprises the following steps:
s1: the method comprises the steps that a wireless sensor network is arranged on a copper plate and strip production line and senses the physical environment around the copper plate and strip production line to obtain sensing information, wherein the sensing information comprises the physical attributes of products and multimedia information of equipment;
s2: setting a plant root growth model based on the sensing information of the copper plate and strip production line;
s3: through a TCP/IP network transmission protocol and a socket data transmission protocol, the sensors of the copper plate and strip production line are mutually associated and information transmission between the upper layer and the lower layer of the system is realized;
s4: the method comprises the steps of combining a knowledge discovery theory based on data mining and a knowledge application theory based on data fusion, identifying physical information and sensing data on a production line, identifying data of sensing information on the production line, and removing redundant information in the sensing information;
s5: setting a constraint model, wherein the constraint model is used for adjusting the production plan;
s6: solving the constraint model through a multi-objective optimization algorithm based on a plant root growth model to obtain an optimal solution of the production plan;
s7: and updating the production plan according to the optimal solution, and executing the updated production plan.
In the present invention, biological experiments have shown that the morpheme concentration information determining the division of plant cells and the growth of root hairs is not given to the cells in advance, but the cell system receives its position information from its surrounding environment, i.e. the soil fertility, and the plant root system shows obvious trophism characteristic based on this information. The physical environment of the copper plate and strip production line is regarded as soil, and various types of logic sensors and physical sensors are connected into the soil and used for receiving various types of data. According to the modeling of the plant rhizome individuals in the differentiation process, the external physical environment information sensed through the concentration of the morpheme is effectively organized and expressed, and is transmitted to the upper layer, so that a uniform context information application interface is provided for application developers.
In a preferred embodiment, the plant root growth model is represented by the following formula:
in the formula, the assumption is that there are n sensors on the production line, Si＝(S1，S2，…，Sn) To indicate a particularA certain sensor, Ei＝(E1，E2，…，En) Indicating perception information of the corresponding sensor; and f () is an objective function of the perception model.
In the preferred embodiment, the concentration of the morpheme at each growing point is determined by the relative position of each point and the environmental information of the position, as is the mechanism of the morpheme concentration generation in the real plant cell. Thus, n growth points correspond to n morpheme concentration values, which change each time a new root hair is generated.
In a preferred embodiment, the S4 includes the following sub-processes:
s4.1: identifying isolated point data in the sensing information by selecting a clustering analysis algorithm or a gray clustering algorithm, correcting the isolated point data, and independently storing the isolated point data after the isolated point data enters a database without deleting the isolated point data;
s4.2: filling up the acquired missing data by adopting a linear interpolation method of near-phase data;
s4.3: performing dimensionality reduction processing on the sensing data through a nonlinear data transformation matrix;
s4.4: and discretizing the continuous attribute values in the perception data, and generalizing the perception data to a higher level through a concept level tree.
In a preferred embodiment, the S6 includes the following steps:
s6.1: initializing seeds according to a plant root growth model, and generating a repeatable natural number linked list L and a non-repeatable natural number linked list I so as to form seeds to be grown, wherein the number of the initial seeds is 2, the initial length of each rhizome is 1, and the threshold value of the distance between growing points is 1;
s6.2: calculating an objective function value and modifying the objective function value by using a constraint condition; performing non-dominant sorting on all individuals, wherein the fitness of each solution is the number of non-dominant layers;
s6.3: selecting growing points according to a non-dominated sorting method and a crowded distance, and selecting the number of the growing points for splitting to be N; the value range of N is [2,64 ];
s6.4: splitting the growing points by a single-point crossing method and a partial matching crossing method;
s6.5: converting a non-repetitive natural number sequence I in an individual into a real number sequence theta;
each individual non-repeating natural number sequence I ═ I (I)1,i2,…,id,…,in) Conversion into the intermediate sequence Ψ ═ (ψ)1,ψ2,…,ψd,…,ψn) The calculation formula is as follows:
ψd＝id-1
converting the intermediate sequence into a real number sequence theta ═ (theta)1,θ2,…,θd,…,θn) The calculation formula is as follows:
θd＝n-ψd+rand
where Ψ represents the set of position indices for Θ in descending order; the rand represents a random real number, and the value range of the rand is [0,1 ];
s6.6: growing the real number sequence theta, and converting the real number sequence theta into a non-repetitive natural number sequence I;
changing theta to (theta)1,θ2,…,θd,…,θn) Performing descending order arrangement to obtain a position index set psi (psi) of theta1,ψ2,…,ψd,…,ψn) Then, the following formula gives I ═ (I)1,i2,…,id,…,in)：
In the formula, d represents the d-th virtual production order;
s6.7: carrying out mutation operation on the non-repetitive natural number sequence I;
s6.8: calculating modified objective function values for all individuals by using constraint conditions, then carrying out non-dominated sorting on the individuals, if the number of the individuals exceeds a preset value, carrying out screening by using a congestion distance algorithm, and if the iteration number reaches the maximum cycle number M, carrying out the step 6.9; otherwise, repeating the step 6.3 to the step 6.7; m is a preset positive integer;
s6.9: and carrying out Pareto optimization, and outputting a Pareto set according to a priority order, namely an optimal production plan.
In a preferred embodiment, the number of iterations is counted by a rule:
and after all individuals are mutated, calculating objective function values, and performing non-dominated sorting, wherein the result is recorded as one iteration.
In a preferred embodiment, the number of cracks in each growing point in S6.4 is 4, and the probability of single-point crossing and the probability of partial matching crossing are 0.85.
In a preferred embodiment, the S5 includes the following sub-processes:
s5.1: the following two decision variables are defined for characterizing the production sequence and production equipment:
wherein i, j is 0,1, …, n; i, j ═ 0 represents a virtual production order, indicating the start and end of production; l stands for equipment, l ═ 1,2, …, m;
s5.2: defining an objective function;
wherein, defining the production adjustment time:
wherein i is not equal to j; i, j is 1,2, …, n, wherein n represents a random positive number; 1,2, …, m, wherein m represents a random positive number; t is tijlIndicating the process setup time between production orders i, j in the process plant l; the T is1(X) represents a production set time;
defining the production time:
wherein i is 1,2, …, n; 1,2, …, m; t is tilRepresenting the processing time of the production order i in the processing equipment l; the T is2(Y) production set time
Defining the total production time:
the total production time is equal to the sum of the production adjustment time and the production time, and the total production time is calculated by the following formula:
wherein f is1(X, Y) represents the total production time;
s5.3: a constraint is defined.
In a preferred embodiment, the S5.3 includes the following sub-processes:
s5.3.1: the order i in the device is followed by one and only one order, which is represented by:
s5.3.2: the order j in the facility is preceded by one and only one order, which is represented by:
s5.3.3: an order can be placed into only one facility or not produced, as represented by the following equation:
s5.3.4: each piece of equipment includes a virtual order in its production, represented by the following equation:
s5.3.5: the total amount of orders being produced does not exceed the capacity of the equipment in the current production cycle, and is represented by the following formula:
wherein, theRepresenting the upper limit of the production capacity of each device in the production period; saidRepresenting the lower limit of the production capacity of each device in the production cycle.
In a preferred embodiment, the S3 includes the following steps:
s3.1: the application model end creates a socket according to the IP address type, the socket type and the TCP protocol;
s3.2: the application model end binds an IP address and a port number for the socket;
s3.3: monitoring a port number request by an application model end socket, and preparing to receive a connection sent by a sensing model end at any time, wherein the socket of the application model end is not opened at the moment;
s3.4: a perception model end creates a socket;
s3.5: the perception model end opens the socket, and tries to connect the server socket according to the IP address and the port number of the application model end;
s3.6: and the application model end socket receives the request of the client socket, is passively opened, and starts to receive the request of the perception model end until the perception model end returns the connection information. When the socket enters a blocking state, the accept method returns until the perception model end returns the connection information, and the next perception model end request is received;
s3.7: the perception model end is successfully connected, and connection state information is sent to the application model end;
s3.8: returning by using a model terminal accept method, and successfully connecting;
s3.9: the perception model end writes information into the socket;
s3.10: reading information by an application model terminal;
s3.11: closing the perception model end;
s3.12: the application model end is closed.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
the firefly algorithm-based bionic intelligent algorithm is simple to realize for optimizing the model, has strong global search capability, high convergence speed and high solution precision, improves the quality and the efficiency of production planning, and also improves the overall utilization rate of equipment on a production line.
Drawings
FIG. 1 is a flow chart of an embodiment.
Fig. 2 is a schematic diagram of sensing data acquisition of a copper plate and strip casting-continuous rolling production line in the embodiment.
FIG. 3 is a flow chart of a multi-objective intelligent algorithm for plant root growth behavior in an embodiment.
FIG. 4 is a pareto frontier chart of the optimization results of the multi-objective intelligent algorithm of the plant root growth behaviors in the embodiment.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product;
it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
As shown in fig. 1, a data-driven copper plate and strip casting-tandem rolling optimization scheduling method includes the following steps:
s1: the sensing data acquisition mode in the high-precision copper strip production is shown in fig. 2, and the sensing data is mainly divided into two types. The first type is that the data changes along with the change of processing space and time, or the data of the change needs to be collected in real time to control in real time, such as melting temperature, environmental humidity, working procedures, positions, number, processing time and the like, and the data are mainly collected by a wireless sensor; the second type is that the data are not changed along with the change of time and space, such as the work station and the operation time of an operator, the name and the number of equipment, the number and the specification of a product and the like, and the data are mainly collected by using an RFID electronic tag.
S2: setting a plant root growth model based on the sensing information of the copper plate and strip production line;
the plant root growth model is represented by the following formula:
in the formula, the assumption is that there are n sensors on the production line, Si＝(S1，S2，…，Sn) Indicating a particular sensor, Ei＝(E1，E2，…，En) Indicating perception information of the corresponding sensor; f () is the objective function of the perceptual model.
S3: the mutual correlation of the sensing elements on the high-precision copper strip production line and the information transmission between the upper layer and the lower layer of the system are realized by utilizing a TCP/IP network transmission protocol and a Socket data transmission protocol. Before data transmission, connection is established first, and then release is carried out,
s3 includes the following steps:
s3.1: the application model end creates a socket according to the IP address type, the socket type and the TCP protocol;
s3.2: the application model end binds an IP address and a port number for the socket;
s3.3: monitoring a port number request by an application model end socket, and preparing to receive a connection sent by a sensing model end at any time, wherein the socket of the application model end is not opened at the moment;
s3.4: a perception model end creates a socket;
s3.5: the perception model end opens the socket, and tries to connect the server socket according to the IP address and the port number of the application model end;
s3.6: and the application model end socket receives the request of the client socket, is passively opened, and starts to receive the request of the perception model end until the perception model end returns the connection information. When the socket enters a blocking state, the accept method returns until the perception model end returns the connection information, and the next perception model end request is received;
s3.7: the perception model end is successfully connected, and connection state information is sent to the application model end;
s3.8: returning by using a model terminal accept method, and successfully connecting;
s3.9: the perception model end writes information into the socket;
s3.10: reading information by an application model terminal;
s3.11: closing the perception model end;
s3.12: the application model end is closed.
S4: the method comprises the steps of combining a knowledge discovery theory based on data mining and a knowledge application theory based on data fusion, identifying physical information and sensing data on a production line, identifying data of sensing information on the production line, and removing redundant information in the sensing information;
s4 includes the following sub-processes:
s4.1: identifying isolated point data in the sensing information by selecting a clustering analysis algorithm or a gray clustering algorithm, correcting the isolated point data, and independently storing the isolated point data after the isolated point data enters a database without deleting the isolated point data;
s4.2: filling up the acquired missing data by adopting a linear interpolation method of near-phase data;
s4.3: performing dimensionality reduction processing on the sensing data through a nonlinear data transformation matrix;
s4.4: and discretizing the continuous attribute values in the perception data, and generalizing the perception data to a higher level through a concept level tree.
S5: and forming task requirements of a high-precision copper strip production line according to a production order, and establishing a high-precision copper strip casting-continuous rolling whole-flow operation scheduling model considering the production capacity of equipment, production process rules, product requirements and other constraints in the order through organic fusion of physical information of the high-precision copper strip. The scheduling model is n scheduling orders, m devices process, each order comprises a plurality of processes, the process sequence of each workpiece and the processing time of different machines are determined, all constraint conditions are met in the processing process, and the optimization goal is that the total production time is equal to the production adjustment time, the production time and the sum of punishments received by the orders without being programmed is minimum;
s5.1: the following two decision variables are defined for characterizing the production sequence and production equipment:
wherein i, j is 0,1, …, n; i, j ═ 0 represents a virtual production order, indicating the start and end of production; l stands for equipment, l ═ 1,2, …, m;
s5.2: defining an objective function;
wherein, defining the production adjustment time:
wherein i is not equal to j; i, j ═ 1,2, …, n, represent random positive numbers; 1,2, …, m, m represents a random positive number; t is tijlIndicating the process setup time between production orders i, j in the process plant l; t is1(X) represents a production set time;
defining the production time:
wherein i is 1,2, …, n; 1,2, …, m; t is tilRepresenting the processing time of the production order i in the processing equipment l; t is2(Y) production set time
Defining the total production time:
the total production time is equal to the sum of the production setup time and the production time, and is calculated by the following formula:
in the formula (f)1(X, Y) represents the total production time;
s5.3: defining a constraint condition:
s5.3.1: the order i in the device is followed by one and only one order, which is represented by:
s5.3.2: the order j in the facility is preceded by one and only one order, which is represented by:
s5.3.3: an order can be placed into only one facility or not produced, as represented by the following equation:
s5.3.4: each piece of equipment includes a virtual order in its production, represented by the following equation:
s5.3.5: the total amount of orders being produced does not exceed the capacity of the equipment in the current production cycle, and is represented by the following formula:
wherein,representing the upper limit of the production capacity of each device in the production period;representing the lower limit of the production capacity of each device in the production cycle.
S6: solving the constraint model through a multi-objective optimization algorithm based on a plant root growth model to obtain an optimal solution of a production plan, wherein a flow chart of the multi-objective intelligent algorithm of the plant root growth behavior is shown in a figure 3;
s6.1: initializing seeds according to a plant root growth model, and generating a repeatable natural number linked list L and a non-repeatable natural number linked list I so as to form seeds to be grown, wherein the number of the initial seeds is 2, the initial length of each rhizome is 1, and the threshold value of the distance between growing points is 1;
s6.2: calculating an objective function value and modifying the objective function value by using a constraint condition; performing non-dominant sorting on all individuals, wherein the fitness of each solution is the number of non-dominant layers;
s6.3: selecting growing points according to a non-dominated sorting method and a crowded distance, and selecting the number of the growing points for splitting to be 4;
s6.4: splitting the growing points by a single-point crossing method and a partial matching crossing method;
s6.5: converting a non-repetitive natural number sequence I in an individual into a real number sequence theta;
each individual non-repeating natural number sequence I ═ I (I)1,i2,…,id,…,in) Conversion into the intermediate sequence Ψ ═ (ψ)1,ψ2,…,ψd,…,ψn) The calculation formula is as follows:
ψd＝id-1
converting the intermediate sequence into a real number sequence theta ═ (theta)1,θ2,…,θd,…,θn) The calculation formula is as follows:
θd＝n-ψd+rand
where Ψ represents the set of position indices for Θ in descending order; rand represents a random real number, and the value range of rand is [0,1 ];
s6.6: growing the real number sequence theta, and converting the real number sequence theta into a non-repetitive natural number sequence I;
changing theta to (theta)1,θ2,…,θd,…,θn) Performing descending order arrangement to obtain a position index set psi (psi) of theta1,ψ2,…,ψd,…,ψn) Then, the following formula gives I ═ (I)1,i2,…,id,…,in)：
Wherein d represents the d-th virtual production order;
s6.7: carrying out mutation operation on the non-repetitive natural number sequence I;
s6.8: calculating modified objective function values for all individuals by using constraint conditions, then carrying out non-dominated sorting on the individuals, if the number of the individuals exceeds a preset value, carrying out screening by using a congestion distance algorithm, and if the iteration number reaches the maximum cycle number of 1000, carrying out the 6.9 step; otherwise, repeating the step 6.3 to the step 6.7;
s6.9: performing Pareto optimization, and outputting Pareto sets according to a priority order, as shown in fig. 4, that is, a set of optimal scheduling schemes.
S7: and (4) transmitting a decision and optimal scheduling control result generated by man-machine interaction to a production line through an actuator network, and receiving feedback.
The terms describing positional relationships in the drawings are for illustrative purposes only and are not to be construed as limiting the patent;
it should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (9)
1. A data-driven copper plate and strip casting-continuous rolling optimization scheduling method is characterized by comprising the following steps:
s1: the method comprises the steps that a wireless sensor network is arranged on a copper plate and strip production line and senses the physical environment around the copper plate and strip production line to obtain sensing information, wherein the sensing information comprises the physical attributes of products and multimedia information of equipment;
s2: setting a plant root growth model based on the sensing information of the copper plate and strip production line;
s3: through a TCP/IP network transmission protocol and a socket data transmission protocol, the sensors of the copper plate and strip production line are mutually associated and information transmission between the upper layer and the lower layer of the system is realized;
s4: the method comprises the steps of combining a knowledge discovery theory based on data mining and a knowledge application theory based on data fusion, identifying physical information and sensing data on a production line, identifying data of sensing information on the production line, and removing redundant information in the sensing information;
s5: setting a constraint model, wherein the constraint model is used for adjusting the production plan;
s6: solving the constraint model through a multi-objective optimization algorithm based on a plant root growth model to obtain an optimal solution of the production plan;
s7: and updating the production plan according to the optimal solution, and executing the updated production plan.
2. The copper plate and strip casting-tandem rolling optimal scheduling method as claimed in claim 1, wherein the plant root growth model is represented by the following formula:
in the formula, the assumption is that there are n sensors on the production line, Si＝(S1，S2，…，Sn) Indicating a particular sensor, Ei＝(E1，E2，…，En) Indicating perception information of the corresponding sensor; and f () is an objective function of the perception model.
3. The optimized scheduling method for casting-tandem casting of copper slabs and strips as claimed in claim 1 or 2, wherein the step S4 comprises the following sub-processes:
s4.1: identifying isolated point data in the sensing information by selecting a clustering analysis algorithm or a gray clustering algorithm, correcting the isolated point data, and independently storing the isolated point data after the isolated point data enters a database without deleting the isolated point data;
s4.2: filling up the acquired missing data by adopting a linear interpolation method of near-phase data;
s4.3: performing dimensionality reduction processing on the sensing data through a nonlinear data transformation matrix;
s4.4: and discretizing the continuous attribute values in the perception data, and generalizing the perception data to a higher level through a concept level tree.
4. The optimized dispatching method for casting-tandem casting of copper slabs and strips as claimed in claim 3, wherein the step S6 comprises the following steps:
s6.1: initializing seeds according to a plant root growth model, and generating a repeatable natural number linked list L and a non-repeatable natural number linked list I so as to form seeds to be grown, wherein the number of the initial seeds is 2, the initial length of each rhizome is 1, and the threshold value of the distance between growing points is 1;
s6.2: calculating an objective function value and modifying the objective function value by using a constraint condition; performing non-dominant sorting on all individuals, wherein the fitness of each solution is the number of non-dominant layers;
s6.3: selecting growing points according to a non-dominated sorting method and a crowded distance, and selecting the number of the growing points for splitting to be N; the value range of N is [2,64 ];
s6.4: splitting the growing points by a single-point crossing method and a partial matching crossing method;
s6.5: converting a non-repetitive natural number sequence I in an individual into a real number sequence theta;
each individual non-repeating natural number sequence I ═ I (I)1,i2,…,id,…,in) Conversion into the intermediate sequence Ψ ═ (ψ)1,ψ2,…,ψd,…,ψn) The calculation formula is as follows:
ψd＝id-1
converting the intermediate sequence into a real number sequence theta ═ (theta)1,θ2,…,θd,…,θn) The calculation formula is as follows:
θd＝n-ψd+rand
where Ψ represents the set of position indices for Θ in descending order; the rand represents a random real number, and the value range of the rand is [0,1 ];
s6.6: growing the real number sequence theta, and converting the real number sequence theta into a non-repetitive natural number sequence I;
changing theta to (theta)1,θ2,…,θd,…,θn) Performing descending order arrangement to obtain a position index set psi (psi) of theta1,ψ2,…,ψd,…,ψn) Then, the following formula gives I ═ (I)1,i2,…,id,…,in)：
In the formula, d represents the d-th virtual production order;
s6.7: carrying out mutation operation on the non-repetitive natural number sequence I;
s6.8: calculating modified objective function values for all individuals by using constraint conditions, then carrying out non-dominated sorting on the individuals, if the number of the individuals exceeds a preset value, carrying out screening by using a congestion distance algorithm, and if the iteration number reaches the maximum cycle number M, carrying out the step 6.9; otherwise, repeating the step 6.3 to the step 6.7; m is a preset positive integer;
s6.9: and carrying out Pareto optimization, and outputting a Pareto set according to a priority order, namely an optimal production plan.
5. The copper plate and strip casting-tandem rolling optimization scheduling method as claimed in claim 4, wherein the number of iterations is counted by a rule:
and after all individuals are mutated, calculating objective function values, and performing non-dominated sorting, wherein the result is recorded as one iteration.
6. The optimized dispatching method for casting-tandem casting of copper slabs and strips as claimed in claim 4 or 5, wherein the number of cracks at each growth point in S6.4 is 4, and the probability of single-point crossing and the probability of partial matching crossing are 0.85.
7. The optimized scheduling method for casting-tandem casting of copper slabs as claimed in claim 6, wherein the step S5 comprises the following sub-processes:
s5.1: the following two decision variables are defined for characterizing the production sequence and production equipment:
wherein i, j is 0,1, …, n; i, j ═ 0 represents a virtual production order, indicating the start and end of production; l stands for equipment, l ═ 1,2, …, m;
s5.2: defining an objective function;
wherein, defining the production adjustment time:
wherein i is not equal to j; i, j is 1,2, …, n, wherein n represents a random positive number; 1,2, …, m, wherein m represents a random positive number; t is tijlIndicating the process setup time between production orders i, j in the process plant l; the T is1(X) represents a production set time;
defining the production time:
wherein i is 1,2, …, n; 1,2, …, m; t is tilRepresenting the processing time of the production order i in the processing equipment l; the T is2(Y) production set time
Defining the total production time:
the total production time is equal to the sum of the production adjustment time and the production time, and the total production time is calculated by the following formula:
wherein f is1(X, Y) represents the total production time;
s5.3: a constraint is defined.
8. The copper plate and strip casting-tandem rolling optimization scheduling method as claimed in claim 7, wherein the S5.3 comprises the following sub-processes:
s5.3.1: the order i in the device is followed by one and only one order, which is represented by:
s5.3.2: the order j in the facility is preceded by one and only one order, which is represented by:
s5.3.3: an order can be placed into only one facility or not produced, as represented by the following equation:
s5.3.4: each piece of equipment includes a virtual order in its production, represented by the following equation:
s5.3.5: the total amount of orders being produced does not exceed the capacity of the equipment in the current production cycle, and is represented by the following formula:
wherein, theRepresenting the upper limit of the production capacity of each device in the production period; saidRepresenting the lower limit of the production capacity of each device in the production cycle.
9. The optimized scheduling method for casting-tandem casting of copper slabs and strips as claimed in claim 1,2, 4, 5, 7 or 8, wherein the step S3 comprises the following steps:
s3.1: the application model end creates a socket according to the IP address type, the socket type and the TCP protocol;
s3.2: the application model end binds an IP address and a port number for the socket;
s3.3: monitoring a port number request by an application model end socket, and preparing to receive a connection sent by a sensing model end at any time, wherein the socket of the application model end is not opened at the moment;
s3.4: a perception model end creates a socket;
s3.5: the perception model end opens the socket, and tries to connect the server socket according to the IP address and the port number of the application model end;
s3.6: and the application model end socket receives the request of the client socket, is passively opened, and starts to receive the request of the perception model end until the perception model end returns the connection information. When the socket enters a blocking state, the accept method returns until the perception model end returns the connection information, and the next perception model end request is received;
s3.7: the perception model end is successfully connected, and connection state information is sent to the application model end;
s3.8: returning by using a model terminal accept method, and successfully connecting;
s3.9: the perception model end writes information into the socket;
s3.10: reading information by an application model terminal;
s3.11: closing the perception model end;
s3.12: the application model end is closed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810386951.5A CN108665094A (en) | 2018-04-26 | 2018-04-26 | A kind of copper plate/strip founding-tandem rolling Optimization Scheduling of data-driven |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810386951.5A CN108665094A (en) | 2018-04-26 | 2018-04-26 | A kind of copper plate/strip founding-tandem rolling Optimization Scheduling of data-driven |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108665094A true CN108665094A (en) | 2018-10-16 |
Family
ID=63781242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810386951.5A Pending CN108665094A (en) | 2018-04-26 | 2018-04-26 | A kind of copper plate/strip founding-tandem rolling Optimization Scheduling of data-driven |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108665094A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111507602A (en) * | 2020-04-10 | 2020-08-07 | 华中科技大学 | Multi-planning-period-oriented two-stage dynamic virtual unit reconstruction method and system |
| CN114833202A (en) * | 2022-04-07 | 2022-08-02 | 中冶赛迪重庆信息技术有限公司 | Blank removing method, system, medium and electronic terminal for improving average temperature of direct rolling |
| CN117590790A (en) * | 2024-01-17 | 2024-02-23 | 青岛创新奇智科技集团股份有限公司 | Intelligent production line monitoring method and system based on industrial large model |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102457536A (en) * | 2010-10-22 | 2012-05-16 | 孔煜 | Multi-sensor adaptive control network platform |
| 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 |
| CN105160433A (en) * | 2015-09-14 | 2015-12-16 | 河海大学常州校区 | Assembly line multi-target modeling method, particle swarm algorithm and optimization scheduling method |
-
2018
- 2018-04-26 CN CN201810386951.5A patent/CN108665094A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102457536A (en) * | 2010-10-22 | 2012-05-16 | 孔煜 | Multi-sensor adaptive control network platform |
| 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 |
| CN105160433A (en) * | 2015-09-14 | 2015-12-16 | 河海大学常州校区 | Assembly line multi-target modeling method, particle swarm algorithm and optimization scheduling method |
Non-Patent Citations (4)
| Title |
|---|
| HAO ZHANG 等: "Root Growth Model for Simulation of Plant Root System and Numerical Function Optimization", 《8TH INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING TECHNOLOGY, ICIC2012》 * |
| 张浩 等: "基于多目标根系生长算法的高精铜锭熔炼作业调度", 《控制理论与应用》 * |
| 彭高辉 等: "数据挖掘中的数据预处理方法", 《华北水利水电学院学报》 * |
| 谦形: "简单理解Socket", 《博客园HTTPS://WWW.CNBLOGS.COM/DOLPHINX/P/ 3460545.HTML》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111507602A (en) * | 2020-04-10 | 2020-08-07 | 华中科技大学 | Multi-planning-period-oriented two-stage dynamic virtual unit reconstruction method and system |
| CN111507602B (en) * | 2020-04-10 | 2022-04-01 | 华中科技大学 | Multi-planning-period-oriented two-stage dynamic virtual unit reconstruction method and system |
| CN114833202A (en) * | 2022-04-07 | 2022-08-02 | 中冶赛迪重庆信息技术有限公司 | Blank removing method, system, medium and electronic terminal for improving average temperature of direct rolling |
| CN114833202B (en) * | 2022-04-07 | 2024-04-12 | 中冶赛迪信息技术(重庆)有限公司 | Method, system, medium and electronic terminal for picking blanks to improve average temperature of straight rolling |
| CN117590790A (en) * | 2024-01-17 | 2024-02-23 | 青岛创新奇智科技集团股份有限公司 | Intelligent production line monitoring method and system based on industrial large model |
| CN117590790B (en) * | 2024-01-17 | 2024-04-12 | 青岛创新奇智科技集团股份有限公司 | Intelligent production line monitoring method and system based on industrial large model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111915410B (en) | Intelligent management and control system for high-dynamic production logistics process | |
| CN102402716B (en) | Intelligent production decision support system | |
| Fengque et al. | Research on design of the smart factory for forging enterprise in the industry 4.0 environment | |
| CN117389236B (en) | Propylene oxide production process optimization method and system | |
| CN106651200A (en) | Electrical load management method and system for industrial enterprise aggregate user | |
| Deng et al. | Metaverse-driven remote management solution for scene-based energy storage power stations | |
| CN105302096A (en) | Factory intelligent scheduling method | |
| Qian et al. | Digital twin driven production progress prediction for discrete manufacturing workshop | |
| Grimaccia et al. | Neuro-fuzzy predictive model for PV energy production based on weather forecast | |
| CN101408769A (en) | On-line energy forecasting system and method based on product ARIMA model | |
| CN107944594B (en) | Short-term load prediction method based on spearman grade and RKELM microgrid | |
| CN117829382A (en) | Intelligent prediction method and system for highway construction progress | |
| CN108665094A (en) | A kind of copper plate/strip founding-tandem rolling Optimization Scheduling of data-driven | |
| CN111258984B (en) | Product quality end-edge-cloud collaborative forecasting method under industrial big data environment | |
| CN112614011A (en) | Power distribution network material demand prediction method and device, storage medium and electronic equipment | |
| CN110119846A (en) | A kind of multiple target deepness belief network for mid-term electric load forecasting | |
| Jimenez et al. | The role of artificial intelligence in Latin Americas energy transition | |
| CN116452121A (en) | Intelligent enterprise inventory management system and management platform | |
| CN105913142B (en) | Method for improving order completion period prediction accuracy by utilizing workshop RFID data | |
| CN105900030A (en) | Method, system, and computer program product for analyzing production and/or process-engineering processes and/or process steps in a plant | |
| Wu | Computational intelligence-based intelligent business intelligence system: concept and framework | |
| CN117494472B (en) | Discrete process optimization method and device based on simulation verification | |
| CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
| CN106056250A (en) | Power distribution network patrol method based on path optimization | |
| Mele et al. | Machine learning platform for profiling and forecasting at microgrid level |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181016 |