CN114764663A - GEP artificial intelligence scheduling method and device based on path and sequencing selection - Google Patents
GEP artificial intelligence scheduling method and device based on path and sequencing selection Download PDFInfo
- Publication number
- CN114764663A CN114764663A CN202110036678.5A CN202110036678A CN114764663A CN 114764663 A CN114764663 A CN 114764663A CN 202110036678 A CN202110036678 A CN 202110036678A CN 114764663 A CN114764663 A CN 114764663A
- Authority
- CN
- China
- Prior art keywords
- machine
- workpiece
- time
- path
- gep
- 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
- 238000000034 method Methods 0.000 title claims abstract description 152
- 238000012163 sequencing technique Methods 0.000 title claims abstract description 27
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 24
- 230000008569 process Effects 0.000 claims abstract description 77
- 238000012545 processing Methods 0.000 claims abstract description 53
- 108090000623 proteins and genes Proteins 0.000 claims abstract description 16
- 230000014509 gene expression Effects 0.000 claims abstract description 15
- 238000004519 manufacturing process Methods 0.000 claims abstract description 11
- 238000007514 turning Methods 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims description 25
- 210000000349 chromosome Anatomy 0.000 claims description 20
- 238000004088 simulation Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 13
- 238000010276 construction Methods 0.000 claims description 9
- 238000003754 machining Methods 0.000 claims description 9
- 230000001681 protective effect Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002759 chromosomal effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06N3/008—Artificial life, i.e. computing arrangements simulating life based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Robotics (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a GEP artificial intelligence scheduling method and a GEP artificial intelligence scheduling device based on path and sequencing selection, which comprise the following steps: step 1: initializing information of a workpiece and machine equipment; and 2, step: updating the current processes of all the workpieces; step 3, judging whether a workpiece needs to be processed or not; and 4, step 4: judging whether a workpiece needs to be assigned to a machine or not; and 5: assigning each workpiece requiring a machine; step 6: if the machine is idle, go to step 7; if no machine is idle, go to step 2; and 7: for each idle machine, calculating a sorting selection rule in a GEP algorithm one by one; and 8: and updating the workpiece state, the machine state and all the information tables, and turning to the step 2. The invention uses gene expression to program for solving, wherein the gene expression comprises two parts of genes and respectively corresponds to the rules of path selection and sequencing selection, and can simultaneously solve the scheduling of path problem and sequencing problem during workpiece processing and improve the processing efficiency during workpiece production and processing.
Description
Technical Field
The invention belongs to the technical field of dynamic scheduling of factories, and particularly relates to a GEP (generic object protocol) artificial intelligence scheduling method and device based on path and sequencing selection.
Background
When the GEP is used for decoding, the GEP reads the characters in the genes in the order from left to right, and then maps the genes into corresponding expression trees according to the grammar rule. This chromosomal structure of GEP combines the advantages of the individual organization methods of GA and GP, so that GEP is far more efficient than GA and GP in solving many problems. The application research result of the gene expression programming in the supervised machine learning shows that the method is very suitable for solving the problems of classification and complex functional relationship discovery. The manufacturing process line for consumer electronics is a complex random dynamic system. For a flexible mixed flow production line, the production machine has some flexibility, i.e. it is assumed that a single workpiece can be processed on different machines. Two sub-problems need to be solved at this time. The first sub-problem is the work piece process, which requires selecting the proper machine to wait for machining. The second sub-problem is that after a machine is vacated, it is necessary to select a suitable workpiece from the workpieces waiting to be processed at the same time for processing. The first sub-problem is the path problem and the second sub-problem is the ordering problem.
There is an urgent need for scheduling that solves both the path sub-problem and the sequencing sub-problem. Therefore, a GEP artificial intelligence scheduling method and device based on path and sorting selection are needed to solve the above problems.
Disclosure of Invention
The invention aims to provide a GEP artificial intelligence scheduling method and device based on path and sequencing selection, which are used for solving by using gene expression programming, wherein the gene expression comprises two parts of genes and respectively corresponds to rules of path selection and sequencing selection, can simultaneously solve the scheduling of path problem and sequencing problem during workpiece processing, improve the processing efficiency during workpiece production and processing and solve the problems in the background technology.
In order to realize the purpose, the invention adopts the following technical scheme: a GEP artificial intelligence scheduling method based on path and sorting selection comprises the following steps:
step 1: initializing information of the workpiece and the machine equipment, wherein the corresponding relation is that CT is 0;
step 2: updating the current working procedure of all workpieces, and the current working procedure of the workpieces and a mapping table P2Mtable (CT) of an optional machine set;
step 3, judging whether a workpiece needs to be processed or not, and if not, ending; if yes, go to step 4;
And 4, step 4: judging whether a workpiece needs to be assigned with a machine, if so, turning to the step 5, and determining a processing machine for all workpieces needing to be processed; if not, turning to step 6;
and 5: calculating a path selection rule for each workpiece needing to be assigned with a machine by using a GEP algorithm, selecting the machine with the highest priority according to the path selection, and placing the workpieces into a processing queue of the machine;
step 6: if the machine is idle, go to step 7; if no machine is idle, go to step 2;
and 7: for each idle machine, calculating a sorting selection rule in a GEP algorithm one by one, and selecting a workpiece procedure with the highest priority according to procedure priority sorting, wherein the machine starts to process the workpiece;
and 8: and updating the workpiece state, the machine state and all the information tables, and turning to the step 2.
Preferably, the gene expression format of the GEP algorithm comprises a function set FS and a terminal set TS, wherein the terminal set TS comprises a TS _ M and a TS _ W, the TS _ M corresponds to a path selection problem, and the TS _ W corresponds to a workpiece selection problem.
Preferably, the function set FS comprises arithmetic operations plus "+", minus "-", multiply "+" and protective division "/", the protective division "/" returns "1" when the divisor is zero, and the set of function sets FS is denoted as FS { +, -,/}.
Preferably, the TS _ M contains elements representing attributes and current state of candidate machine devices and is used to construct a rank for machine selection, the TS _ M selects a device for each artifact and according to a rank priority, the TS _ M set contains the following elements:
t _ FP-Time of finished processes, sum of processing Time of finished processes on the machine;
n _ FP-Number of finished processes, the Number of finished processes on the machine;
t _ WP-Time of waiting process, the sum of the processing Time of the waiting processing procedure on the machine;
n _ WP-Number of waiting processes, Number of waiting processes on the machine;
PT-Process time, the machining time of the current working procedure of the workpiece on the machine;
the TS _ W contains elements representing attributes and current states of candidate workpieces and is used for constructing the sorting of workpiece dispatching rules, the TS _ W is used for selecting corresponding workpieces and procedures according to sorting priorities and aiming at each piece of equipment, and the TS _ W set contains the following elements:
CT-Current time, Current time;
TA-Arrival Time of the workpiece;
TD-Due time, work delivery date;
AT-Arrival time of current process, and the time of the current working procedure of the workpiece;
ST-Starting time of current process, the earliest start time of the current process of the workpiece;
RT-Relaxing time, relaxation time, max { TD-CT-TUP,0}, CT represents the current time;
PT-Processing time of current process, and the Processing time of the current process of the workpiece on the machine;
IT-idle time, dead time of the current working procedure of the workpiece, and idle time of the workpiece;
WT-waiting time, workpiece processing machine wait time;
TUP-time of unfinished processes, total processing time of the number of unfinished processes remaining in the workpiece;
NUP-number of unfinished processes, the number of unfinished processes remaining in the workpiece;
TWP-time of waiting process on one machine, waiting for total processing time of the next process on the processing machine of the workpiece;
MT-Earlie free time of the machine for the current process, processes the Earliest idle time of the current process machine.
Preferably, the GEP algorithm is set as a binary chromosome, two chromosomes in the binary chromosome respectively correspond to the machine assignment rule code of the path and the workpiece dispatch rule code of the workpiece sorting, that is, the binary chromosome includes a path part and a sorting part, the sub-chromosomal gene head part of the path part is composed of elements in FS and TS _ M and the sub-chromosomal gene head part of the path part is composed of elements in TS _ M, the sub-chromosomal gene head part of the sorting part is composed of elements in FS and TS _ W and the sub-chromosome tail part is composed of elements in TS _ W, the rule corresponding to the machine selection path subproblem is F ═ PT) + (PT × T _ WP), and the rule corresponding to the process selection sorting subproblem is: f ═ (WT + PT) + (ST-NUP).
The invention also provides a GEP artificial intelligence scheduling method device based on path and sequencing selection, which comprises a rule construction module and an evaluation module, wherein the rule construction module is electrically connected with the evaluation module, the rule construction module comprises a starting unit, a population initialization unit, an EGP operation unit and a new population forming unit, and the evaluation module comprises a simulation evaluation system unit.
Preferably, the starting unit is electrically connected with the population initializing unit, the population initializing unit is electrically connected with the EGP operating unit, and the EGP operating unit is electrically connected with the new population forming unit.
Preferably, the starting unit is configured to pre-define a function set, a terminal set, and algorithm parameters, the population initialization unit is configured to create an initial population, the EGP operation unit is configured to calculate a fitness value of an individual of the created initial population, and determine whether the fitness value meets a termination condition, if so, a final result is output, the end is performed, and if not, a plurality of sets of feasible strategies are generated by using an offline learning method through the EGP operation unit in combination with a scheduling rule automatically constructed by a simulation model for online experiments, so as to perform population evolution and iteration.
Preferably, the simulation evaluation system unit is composed of basic information and dynamic information of people, machines, materials, methods and rings in a workshop, the evaluation module establishes a simulation model according to production characteristics, and random examples generated through the simulation model are used for evaluating the advantages and disadvantages of different dynamic scheduling rules and providing candidate rule strategies for actual online scheduling.
Preferably, the population initialization unit is electrically connected with the evaluation module, and the evaluation module evaluates the state of the population according to the state of the population and the basic information and the dynamic information of the workshop man-machine material method loop.
The invention has the technical effects and advantages that: compared with the prior art, the GEP artificial intelligence scheduling method and device based on path and sequencing selection provided by the invention have the following advantages: the method is used for solving by programming a gene expression, wherein the gene expression comprises two parts of genes and respectively corresponds to the rules of path selection and sequencing selection, the scheduling of the path problem and the sequencing problem during workpiece processing can be simultaneously solved, and the processing efficiency is improved during workpiece production and processing.
Drawings
FIG. 1 is a flow chart of a GEP artificial intelligence scheduling method based on path and sorting selection according to the present invention;
FIG. 2 is a system block diagram of an apparatus of the GEP artificial intelligence scheduling method based on path and sorting selection according to the present invention;
FIG. 3 is a book of the expression of the inner path chromosomes according to the present invention;
FIG. 4 is a book of ordered chromosome expression in accordance with the present invention;
FIG. 5 is a schematic of a binary genome.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely below, 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. The specific embodiments described herein are merely illustrative of the invention and do not delimit the invention. 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.
The invention provides a technical scheme as shown in figures 1-4: a GEP artificial intelligence scheduling method based on path and sequencing selection comprises the following steps:
step 1: initializing information of the workpiece and machine equipment, wherein the corresponding relation is that CT is 0;
and 2, step: updating the current working procedure of all workpieces, and the current working procedure of the workpieces and a mapping table P2Mtable (CT) of an optional machine set;
Step 3, judging whether a workpiece needs to be processed or not, and if not, ending; if yes, go to step 4;
and 4, step 4: judging whether a workpiece needs to be assigned with a machine, if so, turning to the step 5, and determining a processing machine for all workpieces needing to be processed; if not, turning to step 6;
and 5: calculating a path selection rule for each workpiece needing to be assigned with a machine by using a GEP algorithm, selecting the machine with the highest priority according to the path selection, and placing the workpieces into a processing queue of the machine;
step 6: if the machine is idle, go to step 7; if no machine is idle, go to step 2;
and 7: for each idle machine, calculating a sorting selection rule in a GEP algorithm one by one, and selecting a workpiece procedure with the highest priority according to procedure priority sorting, wherein the machine starts to process the workpiece;
and 8: and updating the workpiece state, the machine state and all the information tables, and turning to the step 2.
The genetic expression format of the GPE algorithm comprises a function set FS and a terminal set TS, wherein the terminal set TS comprises TS _ M (machine) and TS _ W (work piece), the TS _ M (machine) corresponds to a path selection problem, and the TS _ W (work piece) corresponds to a workpiece selection problem. The function set FS contains arithmetic operations plus "+", minus "-", multiply "+" and protective division "/", the protective division "/" returns "1" when the divisor is zero, the set of function sets FS is denoted FS { +, -,/(protective division) }; wherein the TS _ M (machine) contains elements representing attributes and current state of candidate machine devices and is used to construct a ranking for machine selection, the TS _ M (machine) selects a device for each artifact and according to a ranking priority, the TS _ M (machine) set contains the following elements:
T _ FP-Time of finished processes, sum of processing Time of finished processes on the machine;
n _ FP-Number of finished processes, the Number of finished processes on the machine;
t _ WP-Time of waiting process, the sum of the processing Time of the waiting processing procedure on the machine;
n _ WP-Number of waiting processes, Number of waiting processes on the machine;
PT-Process time, the machining time of the current working procedure of the workpiece on the machine;
the TS _ W (workpieces) contains elements representing attributes and current states of candidate workpieces and is used for constructing the sorting of workpiece dispatching rules, the TS _ W (workpieces) selects corresponding workpieces and procedures for each piece of equipment according to sorting priorities, and the TS _ W (workpieces) set contains the following elements:
CT-Current time, Current time;
TA-Arrival Time of the workpiece;
TD-Due time, work delivery date;
AT-Arrival time of current process, and the time of the current working procedure of the workpiece;
ST-Starting time of current process, the earliest start time of the current process of the workpiece;
RT-Relaxing time, relaxation time, max { TD-CT-TUP,0}, CT represents the current time;
PT-Processing time of current process, the Processing time of current working procedure of workpiece on machine;
IT-idle time, dead time of the current working procedure of the workpiece, and idle time of the workpiece;
WT-waiting time, workpiece processing machine wait time;
TUP-time of unfinished processes, the total processing time of the number of unfinished processes remaining in the workpiece;
NUP-number of unfinished processes, and the number of remaining unfinished processes of the workpiece;
the TWP-time of waiting processes on one machine, waiting for the total processing time of the process on the processing machine of the next process of the workpiece;
MT-Earlie free time of the machine for the current process, processing the Earliest idle time of the machine in the current process.
The GPE algorithm is set as a binary chromosome, two chromosomes in the binary chromosome respectively correspond to a machine assignment rule code of a path and a workpiece assignment rule code of workpiece ordering, that is, the binary chromosome includes a path part and an ordering part, a sub-intrachromosomal gene head of the path part is composed of elements in FS and TS _ m (machine), and a sub-intrachromosomal gene tail of the path part is composed of elements in TS _ m (machine), a sub-intrachromosomal gene head of the ordering part is composed of elements in FS and TS _ w (machine), and a sub-chromosome tail of the ordering part is composed of elements in TS _ w (machine), a rule corresponding to a machine selection path sub-problem is F PT (PT) + (PT T _ WP), and a rule corresponding to a process selection ordering sub-problem is: f ═ (WT + PT) + (ST-NUP);
Referring to FIG. 5, the following is an example of a binary chromosome set:
the chromosome of the pathfinder is a monogenic chromosome, the length of the head is 7, and the tail is 5; the sequencing sub chromosome is a two-gene chromosome, the head length is 3, and the tail length is 4; l _ Tail ═ L _ head: (n (fs) -1) + 1; l _ Tail is the Tail length; l _ head is the head length; n (FS) is the size of the function set FS; the following is only used as an example to illustrate how to construct a chromosome, the tail length and the head length of which do not necessarily conform to the above formula relationship, and the example is only used to illustrate how to construct, and does not mean that the lengths are not correct, and all designs in the example can be expanded mathematically at will;
the basic problem is set up:
n: total number of workpieces;
w: total workpiece set { W1, W2, …, Wn };
m: total number of machines;
omega: total machine set { M1, M2, …, Mm };
i, e: machine number, i, e ═ 1,2, 3;
j, k: workpiece number, j, k is 1,2, 3;
Wj(CT): a current time process of the jth workpiece;
hjtotal number of processes for the jth workpiece;
l, tool number, l ═ 1,2,3, …, hj;
Ωjh: optional processing machine set of the h procedure of the jth workpiece;
Mjh: the optional number of processing machines of the h procedure of the jth workpiece;
Ojh: the h procedure of the jth workpiece;
Mijh: the h procedure of the jth workpiece is processed on a machine i;
pijh: the machining time of the h procedure of the jth workpiece on the machine i;
sjh: the machining starting time of the h procedure of the jth workpiece;
cjh: the machining completion time of the h procedure of the jth workpiece;
dj: delivery date of j workpieces;
Cj: completion time for jth workpiece;
Cmax: a maximum completion time;
xijh1 if step OjhSelecting a machine i; o isijhIf the process O is 0jhMachine i is not selected;
yijhklif process O is equal to 1ijhPrior to OiklProcessing; y isijhklIf the process O is 0ijhNot prior to OiklProcessing;
the relationship table for the machines corresponding to the current process for all workpieces is as follows:
the Table is defined as P2Mtable (CT), Process to Machine Mapping Table is the Mapping Table of the selectable processing Machine corresponding to the current Process of all the workpieces; wherein a value of 1 indicates that processing on the equipment is possible and a value of 0 indicates that processing on the equipment is not possible; one workpiece is processed on multiple devices, and one device can process different workpieces, which indicates that the production line has flexibility.
The invention also provides a GEP artificial intelligence scheduling method device based on path and sequencing selection, which comprises a rule construction module and an evaluation module, wherein the rule construction module is electrically connected with the evaluation module, the rule construction module comprises a starting unit, a population initialization unit, an EGP operation unit and a new population forming unit, and the evaluation module comprises a simulation evaluation system unit;
The start unit is electrically connected with the population initialization unit, the population initialization unit is electrically connected with the EGP operation unit, and the EGP operation unit is electrically connected with the new population forming unit;
the system comprises a starting unit, a population initialization unit, an EGP operation unit and an EGP operation unit, wherein the starting unit is used for predefining a function set, a terminal set and algorithm parameters, the population initialization unit is used for creating an initial population, the EGP operation unit is used for calculating the fitness value of an individual of the created initial population and confirming whether the fitness value meets a termination condition, if so, a final result is output, the end is achieved, and if not, a plurality of groups of feasible strategies are generated by the EGP operation unit by adopting an offline learning method and combining with a dispatching rule automatically constructed by a simulation model for online experiments and used for population evolution and iteration;
the system comprises a simulation evaluation system unit, an evaluation module and a control module, wherein the simulation evaluation system unit is composed of basic information and dynamic information of a person, a machine, a material, a method and a ring of a workshop, the evaluation module establishes a simulation model according to production characteristics, and random examples generated through the simulation model are used for evaluating the advantages and disadvantages of different dynamic scheduling rules and providing candidate rule strategies for actual online scheduling;
The evaluation module evaluates the state of the population according to the state of the population and the basic information and the dynamic information of the workshop man-machine material method loop.
The working principle is as follows: the method is used for solving by programming a gene expression, wherein the gene expression comprises two parts of genes and respectively corresponds to the rules of path selection and sequencing selection, the scheduling of the path problem and the sequencing problem during workpiece processing can be simultaneously solved, and the processing efficiency is improved during workpiece production and processing.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still make modifications to the technical solutions described in the foregoing embodiments, or make equivalent substitutions and improvements to part of the technical features of the foregoing embodiments, and any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A GEP artificial intelligence scheduling method based on path and sorting selection is characterized in that: the method comprises the following steps:
Step 1: initializing information of the workpiece and machine equipment, wherein the corresponding relation is that CT is 0;
step 2: updating the current working procedures of all workpieces, and the current working procedures of the workpieces and a mapping table P2Mtable of an optional machine set when CT is equal to CT + 1;
step 3, judging whether a workpiece needs to be processed or not, and if not, ending; if yes, go to step 4;
and 4, step 4: judging whether a workpiece needs to be assigned with a machine, if so, turning to the step 5, and determining a processing machine for all workpieces needing to be processed; if not, turning to step 6;
and 5: calculating a path selection rule for each workpiece needing to be assigned with a machine by using a GEP algorithm, selecting the machine with the highest priority according to the path selection, and placing the workpieces into a processing queue of the machine;
step 6: if the machine is idle, go to step 7; if no machine is idle, go to step 2;
and 7: for each idle machine, calculating a sorting selection rule in a GEP algorithm one by one, and selecting a workpiece procedure with the highest priority according to procedure priority, wherein the machine starts to process the workpiece;
and 8: and updating the workpiece state, the machine state and all the information tables, and turning to the step 2.
2. The GEP artificial intelligence scheduling method based on path and sorting selection according to claim 1, characterized in that: the gene expression format of the GEP algorithm comprises a function set FS and a terminal set TS, wherein the terminal set TS comprises a TS _ M and a TS _ W, the TS _ M corresponds to a path selection problem, and the TS _ W corresponds to a workpiece selection problem.
3. The GEP artificial intelligence scheduling method based on path and sorting selection as claimed in claim 2, wherein: the function set FS contains arithmetic operations plus "+", minus "-", multiply "-", and protective division "/", which returns "1" when the divisor is zero, the set of function sets FS being denoted FS { +, -,/}.
4. The GEP artificial intelligence scheduling method based on path and sequencing selection of claim 3, characterized in that: the TS _ M contains elements representing attributes and current state of candidate machine devices and is used to construct a rank for machine selection, the TS _ M selects a device for each artifact and according to a rank priority, the TS _ M set contains the following elements:
t _ FP-Time of finished processes, sum of processing Time of finished processes on the machine;
n _ FP-Number of finished processes, the Number of processed processes on the machine;
t _ WP-Time of waiting processes, the sum of the machining Time of waiting machining processes on the machine;
n _ WP-Number of waiting processes, the Number of waiting processes on the machine;
PT-Process time, the machining time of the current working procedure of the workpiece on the machine;
The TS _ W contains elements representing attributes and current states of candidate workpieces and is used for constructing the sorting of workpiece dispatching rules, the TS _ W is used for selecting corresponding workpieces and procedures according to sorting priorities and aiming at each piece of equipment, and the TS _ W set contains the following elements:
CT-Current time, Current time;
TA-Arrival Time of the workpiece;
TD-Due time, work delivery date;
AT-Arrival time of current process, and the time of the current working procedure of the workpiece;
ST-Starting time of current process, the earliest Starting time of the current process of the workpiece;
RT-Relaxing time, relaxation time, max { TD-CT-TUP,0}, CT represents the current time;
PT-Processing time of current process, the Processing time of current working procedure of workpiece on machine;
IT-idle time, dead time of the current working procedure of the workpiece, and idle time of the workpiece;
WT-waiting time, workpiece processing machine wait time;
TUP-time of unfinished processes, total processing time of the number of unfinished processes remaining in the workpiece;
NUP-number of unfinished processes, the number of unfinished processes remaining in the workpiece;
TWP-time of waiting process on one machine, waiting for total processing time of the next process on the processing machine of the workpiece;
MT-Earlie free time of the machine for the current process, processing the Earliest idle time of the machine in the current process.
5. The GEP artificial intelligence scheduling method based on path and sequencing selection of claim 1, characterized in that: the GEP algorithm is set as a binary chromosome, two chromosomes in the binary chromosome respectively correspond to a machine assignment rule code of a path and a workpiece dispatch rule code of workpiece sequencing, that is, the binary chromosome comprises a path part and a sequencing part, the heads of sub-chromosomal genes of the path part are composed of elements in FS and TS _ M, the tails of sub-chromosomal genes of the path part are composed of elements in TS _ M, the heads of sub-chromosomal genes of the sequencing part are composed of elements in FS and TS _ W, and the tails of sub-chromosomal genes of the sequencing part are composed of elements in TS _ W, a rule corresponding to a machine selection path sub-problem is F ═ PT) + (PT × T _ WP), and a rule corresponding to a process selection sequencing sub-problem is: f ═ (WT + PT) + (ST-NUP).
6. The device for GEP artificial intelligence scheduling method based on path and sequencing selection according to any one of claims 1 to 5, comprising a rule construction module and an evaluation module, characterized in that: the rule construction module is electrically connected with the evaluation module, the rule construction module comprises a starting unit, a population initialization unit, an EGP operation unit and a new population forming unit, and the evaluation module comprises a simulation evaluation system unit.
7. The apparatus of the GEP artificial intelligence scheduling method based on path and order selection according to claim 6, wherein: the start unit is electrically connected with the population initialization unit, the population initialization unit is electrically connected with the EGP operation unit, and the EGP operation unit is electrically connected with the new population forming unit.
8. The apparatus of the GEP artificial intelligence scheduling method based on path and order selection of claim 7, wherein: the system comprises a starting unit, a population initialization unit, an EGP operation unit and an EGP operation unit, wherein the starting unit is used for predefining a function set, a terminal set and algorithm parameters, the population initialization unit is used for creating an initial population, the EGP operation unit is used for calculating the fitness value of an individual of the created initial population and confirming whether the fitness value meets a termination condition, if so, a final result is output, the completion is carried out, and if not, a plurality of groups of feasible strategies are generated by adopting an offline learning method through the EGP operation unit and combining with a scheduling rule automatically constructed by a simulation model for online experiments and used for population evolution and iteration.
9. The apparatus of the GEP artificial intelligence scheduling method based on path and order selection according to claim 8, wherein: the simulation evaluation system unit is composed of basic information and dynamic information of a person, a machine, a material, a method and a ring of a workshop, the evaluation module establishes a simulation model according to production characteristics, and random examples generated through the simulation model are used for evaluating the advantages and disadvantages of different dynamic scheduling rules and providing candidate rule strategies for actual online scheduling.
10. The device for GEP artificial intelligence scheduling method based on path and order selection according to claim 9, characterized in that: the population initialization unit is electrically connected with the evaluation module, and the evaluation module evaluates the state of the population according to the state of the population and the basic information and the dynamic information of the workshop man-machine material method loop.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110036678.5A CN114764663A (en) | 2021-01-12 | 2021-01-12 | GEP artificial intelligence scheduling method and device based on path and sequencing selection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110036678.5A CN114764663A (en) | 2021-01-12 | 2021-01-12 | GEP artificial intelligence scheduling method and device based on path and sequencing selection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114764663A true CN114764663A (en) | 2022-07-19 |
Family
ID=82363332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110036678.5A Pending CN114764663A (en) | 2021-01-12 | 2021-01-12 | GEP artificial intelligence scheduling method and device based on path and sequencing selection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114764663A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106094757A (en) * | 2016-07-15 | 2016-11-09 | 郑州航空工业管理学院 | A kind of dynamic flexible solving job shop scheduling problem control method based on data-driven |
| CN111382915A (en) * | 2018-12-27 | 2020-07-07 | 沈阳高精数控智能技术股份有限公司 | Flexible job shop scheduling method for co-fusion AGV |
-
2021
- 2021-01-12 CN CN202110036678.5A patent/CN114764663A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106094757A (en) * | 2016-07-15 | 2016-11-09 | 郑州航空工业管理学院 | A kind of dynamic flexible solving job shop scheduling problem control method based on data-driven |
| CN111382915A (en) * | 2018-12-27 | 2020-07-07 | 沈阳高精数控智能技术股份有限公司 | Flexible job shop scheduling method for co-fusion AGV |
Non-Patent Citations (1)
| Title |
|---|
| 聂黎: "基于基因表达式编程的车间动态调度方法的研究" * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109598416B (en) | Dynamic scheduling system and scheduling method for composite material workshop | |
| CN104268722B (en) | Dynamic flexible job-shop scheduling method based on multi-objective Evolutionary Algorithm | |
| CN108460463B (en) | High-end equipment assembly line production scheduling method based on improved genetic algorithm | |
| CN101901425A (en) | Flexible job shop scheduling method based on multi-species coevolution | |
| CN105700495B (en) | Flexible job shop scheduling machine choice method based on process time grade | |
| CN115310794A (en) | Man-machine cooperation assembly line balancing method and device | |
| CN112882449A (en) | Energy consumption optimization scheduling method for multi-variety small-batch multi-target flexible job shop | |
| CN116227874B (en) | Flexible job shop scheduling method and device based on genetic algorithm | |
| Huang et al. | An improved genetic algorithm for job-shop scheduling problem with process sequence flexibility | |
| CN115609593B (en) | Multi-type robot man-machine cooperative assembly scheduling method and device | |
| CN108053152A (en) | The method that improved adaptive GA-IAGA based on polychromatic sets solves dynamic job shop scheduling | |
| CN115700639B (en) | Intelligent production scheduling method, device, equipment and storage medium | |
| CN114036717A (en) | Method and device for determining cutting scheme of steel bar blanking and terminal equipment | |
| CN113901728B (en) | Computer second-class assembly line balance optimization method based on migration genetic algorithm | |
| CN116880424A (en) | Multi-robot scheduling method and device based on multi-objective optimization | |
| CN113848904B (en) | Method for optimizing task allocation of multiple mobile robots based on punishment energy consumption | |
| CN114764663A (en) | GEP artificial intelligence scheduling method and device based on path and sequencing selection | |
| CN116993135A (en) | Multi-stage sequencing and reservation scheduling method and device based on waiting time constraint | |
| CN111985841A (en) | Injection molding workshop scheduling method and system based on improved genetic algorithm | |
| He et al. | Improvements to genetic algorithm for flexible job shop scheduling with overlapping in operations | |
| CN113283819B (en) | Job Shop scheduling problem solving method and system based on rule decoding | |
| CN114676987A (en) | Intelligent flexible job shop active scheduling method based on hyper-heuristic algorithm | |
| CN114648232A (en) | Cloud resource flexible job scheduling method based on improved chimpanzee optimization algorithm | |
| Imad et al. | Solving assembly line balancing problem using a hybrid genetic algorithm with zoning constraints | |
| Quyen et al. | Dynamic programming to solve resource constrained assembly line balancing problem in footwear manufacturing |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220719 |