CN116681248A - Novel gypsum thick plate production beat control method - Google Patents
Novel gypsum thick plate production beat control method Download PDFInfo
- Publication number
- CN116681248A CN116681248A CN202310665383.3A CN202310665383A CN116681248A CN 116681248 A CN116681248 A CN 116681248A CN 202310665383 A CN202310665383 A CN 202310665383A CN 116681248 A CN116681248 A CN 116681248A
- Authority
- CN
- China
- Prior art keywords
- gypsum
- time
- production
- period
- group
- 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
- 229910052602 gypsum Inorganic materials 0.000 title claims abstract description 148
- 239000010440 gypsum Substances 0.000 title claims abstract description 148
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 129
- 238000000034 method Methods 0.000 title claims abstract description 84
- 238000006703 hydration reaction Methods 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims description 27
- 239000002002 slurry Substances 0.000 claims description 25
- 238000003756 stirring Methods 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 22
- 239000002994 raw material Substances 0.000 claims description 16
- 239000013598 vector Substances 0.000 claims description 16
- 238000012546 transfer Methods 0.000 claims description 15
- 230000035772 mutation Effects 0.000 claims description 13
- 230000035484 reaction time Effects 0.000 claims description 12
- 230000002068 genetic effect Effects 0.000 claims description 11
- 230000007306 turnover Effects 0.000 claims description 9
- 239000004568 cement Substances 0.000 claims description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 210000000349 chromosome Anatomy 0.000 claims description 5
- 230000014759 maintenance of location Effects 0.000 claims description 5
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000012248 genetic selection Methods 0.000 claims description 4
- 238000013178 mathematical model Methods 0.000 claims description 4
- 108090000623 proteins and genes Proteins 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 4
- 230000008878 coupling Effects 0.000 abstract description 2
- 238000010168 coupling process Methods 0.000 abstract description 2
- 238000005859 coupling reaction Methods 0.000 abstract description 2
- 238000005457 optimization Methods 0.000 description 4
- 210000004027 cell Anatomy 0.000 description 2
- 238000010353 genetic engineering Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 238000013019 agitation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- PASHVRUKOFIRIK-UHFFFAOYSA-L calcium sulfate dihydrate Chemical compound O.O.[Ca+2].[O-]S([O-])(=O)=O PASHVRUKOFIRIK-UHFFFAOYSA-L 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000010412 perfusion Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0633—Workflow analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Genetics & Genomics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Physiology (AREA)
- Mathematical Physics (AREA)
- Manufacturing & Machinery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
Abstract
The invention relates to a novel method for controlling the production takt time of a thick gypsum plate, and belongs to the technical field of thick gypsum plate production. Aiming at the characteristics of strong constraint and coupling performance, strong limiting conditions of gypsum hydration reaction and the like of the novel gypsum thick plate production system, the invention provides a production takt control method of the novel gypsum thick plate production system. Compared with the production beat of manual production scheduling and fixing, the invention can effectively optimize the total demoulding delay time along with the change of the production proportion, thereby improving the yield of the production line and reducing the failure rate of the system.
Description
Technical Field
The invention belongs to the technical field of gypsum thick plate production, and relates to a novel gypsum thick plate production takt control method.
Background
When phosphogypsum is used as a raw material to produce gypsum products, the condition that gypsum slurry is quickly solidified and a mould is damaged easily occurs. When hydration reaction time and transfer system mismatch, just probably appear stirring after finishing in the drawing of patterns district inside thick liquids in mould dolly and not reach the initial setting time, the unable drawing of patterns's condition, and then cause the gypsum thick liquids in the agitator tank to stir continually, still probably cause equipment damage when wasing the energy. Therefore, operators need to schedule production according to the setting time of the gypsum slurry during the production process. However, the setting process of gypsum involves many factors such as fluctuation of production conditions, fluctuation of raw material components, and the like. Because of the fluctuation of the weight of the raw materials of the gypsum slurry which are actually weighed, the hydration reaction time of different gypsum slurry production is different, and the production takt time control problem is caused.
In the production process, the gypsum slurry 1 on the two conveying lines, conveying line 1 reaches the initial setting time, the demolding is carried out in the demolding area, the gypsum slurry 2 on conveying line 2 also reaches the initial setting time at the moment, but at the moment, the demolding area is used by the gypsum slurry 1, and the demolding of the gypsum slurry 2 cannot be carried out until the demolding of the gypsum slurry 1 is completed. The time difference from the time when the gypsum slurry 2 reaches the initial setting time to the time when the gypsum slurry 2 starts to be demolded is called a demold pulling period, and generally, the greater the demold pulling period, the greater the failure rate in the production process. The gypsum hydration reaction time and the transfer system in the gypsum thick plate production process have strong coupling.
At present, the mode of producing gypsum thick plates in workshops mainly relies on workshop main pipes and experience of field workers to conduct manual production, and the fixed production beats are set in a manual experience mode, so that the production efficiency of a production system is low, and the production failure rate is high. Most tact optimization directions are optimized with known processing times. For the novel gypsum thick plate production system with complex hydration reaction and unknown reaction time, the real-time performance cannot be met, the production efficiency is affected, and the production failure rate is increased.
Disclosure of Invention
In view of the above, the invention aims to provide a novel method for controlling the production takt time of a thick gypsum plate, which is used for establishing a production takt time optimization model for the production process of the thick gypsum plate so as to solve the problems of low production efficiency, high production failure rate and the like of a production system caused by mismatching of the hydration reaction time of gypsum and a transfer system and manual production of fixed production takt time.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a novel gypsum thick plate production beat control method comprises the steps of establishing a production process mathematical model, namely a production beat model, according to the production process of a novel gypsum thick plate, and setting an objective function and constraint conditions for minimizing the maximum finishing time and the total demolding delay time of the production beat model; and optimizing the production beats by adopting a second generation Non-dominant sorting genetic algorithm (Non-dominated Sorting Genetic Algorithm-II, NSGA-II), and decoding by using a priority-based machine allocation strategy and a multi-stage right shift adjustment strategy based on a time window to obtain a scheduling scheme capable of simultaneously optimizing the maximum finishing time and the total demolding and delay.
The production process constraint of the novel gypsum thick plate is as follows:
the weights of the weighed gypsum, cement and water are known, and the environmental temperature of a production workshop is not greatly changed;
the priority of each group of gypsum thick plates is the same;
the production process comprises stirring, pouring, transferring in an initial setting area, initial setting forming and demoulding;
all machines are available in the initial state, but there is priority;
no faults occur in the production process, and the production cannot be interrupted after the start.
Further, the takt model is as follows:
there are n groups of gypsum thick plate raw materials which are weighed in advance, the raw materials need to be produced through m working procedures, o (j) machines are arranged on the j th working procedure, p mould trolleys are arranged on each conveying line, and the processing time of each group of gypsum thick plates on part of working procedures needs to be predicted through a relevant vector machine;
in the initial setting forming process, a plurality of groups of mould trolleys can be simultaneously initially set, and the first-in first-out principle is satisfied; in other working procedures, one production machine can only process one group of thick gypsum boards at the same time, and the starting condition of the transfer system turnover in the initial setting area is that the next pouring is finished, the demolding is finished and no turnover is carried out between the other transport line and the return line;
the mass matrix of gypsum board stock to be produced is represented as follows:
wherein M is sgn M snn And M wn Respectively representing the weights of gypsum, cement and water in the weighed gypsum raw materials, and each column of vectors represents a group of gypsum raw materials;
the hydration reaction time vector for the gypsum board of group a is shown below:
T a ＝[T jba ,T gza ,T cna ] T
wherein T is a Represents a hydration reaction time vector, a=1, 2, …, n, T jba 、T gza And T cna Respectively representing the stirring, pouring and setting removal time of the gypsum thick plate of the group a;
for any set of gypsum slabs production sequence pi= [ pi (1), pi (2), …, pi (n)]Setting S ij Indicating the start time, O, of the jth process of the ith set of gypsum slabs ij Indicating the processing time, E ij Indicating the end time, Z i The mold release downtime of the gypsum board is shown, D (pi (i), pi (i ')) is the start production interval of two adjacent gypsum boards, i' is the serial number of the next gypsum board of the i-th gypsum board.
According to the established takt model, the production process of the gypsum thick plate is divided into a starting period, a production period and an ending period; in the production process, the stirring and pouring equipment operates in a starting period and a production period, the transfer system equipment operates in the starting period, the production period and the end period, and the demolding equipment operates in the production period and the end period.
Further, an objective function and constraints that minimize the maximum finishing time and minimize the total demold hold time are determined from the production process as follows:
the conditions during the start-up period are:
1≤i≤2p+2
wherein, p represents that p mould trolleys are arranged on each transport line; in the stirring and pouring process, the maximum processing time interval between the ith group of gypsum thick plates and the ith' group of gypsum thick plates in the same stirring tank is as follows:
production start time S of the ith set of gypsum slabs i1 The formula is as follows:
S i1 ＝S (i-1)1 +D(π(i),π(i′))
the conditions during the production period are:
2p+3≤i≤n
the demolding process start time is expressed as:
S i4 ＝max{S (i+2p+2)2 +t 2 ,T cni }
wherein T is cni Representation, t 2 Indicating the time during the turnaround that demolding is allowed to begin;
the mold release hold-off time is expressed as:
the starting conditions of the transfer system turnover procedure in the initial setting zone are represented by the following formula:
S i2 ＝max{S (i-2p-2)4 ,S (i-1)2 }
the maximum processing time interval between the i-th set of gypsum planks and the i' -th set of gypsum planks is determined under the condition that the conditions of the starting period and the production period are satisfied:
calculating the starting time and the pulling time of the demoulding process in the end period by adopting a fixed time interval mode, namely, the demoulding starting time depends on the initial setting time or the time of starting demoulding of a group of gypsum thick plates, and the time for one-time operation of a transfer system is assumed to be t sum The demolding start time and demolding delay time are as follows:
S i4 ＝max(S (i-1)4 +t 1 ,T cni )+t sum
definition of decision variable X ijk A 0-1 decision variable, 1 if the i-th set of gypsum slabs are arranged on the k-th processing machine at the j-th process step, or 0 otherwise;
definition of decision variable Y ijk1 A decision variable of 0-1, 1 if the ith set of gypsum slabs is arranged on the jth process in the ith process order on the kth processing machine, or 0 otherwise;
the constraint relationship is obtained as follows:
S i(j+1) ＝S ij +O ij ,j＝1,2,3
E ij ＝S ij +O ij
wherein B is ij Indicating a start time;
the objective function to minimize the maximum finishing time is:
f 1 ＝min(C max (π))
the objective function to minimize the total demold hold time is:
furthermore, in the second generation non-dominant sorting genetic algorithm, the coding mode adopts integer coding, the quantity of gypsum thick plates to be produced is set to be the chromosome length, and the population individuals are described by pi= [ pi (1), pi (2), … and pi (n) ].
Decoding using a priority-based machine allocation strategy and a time window-based multi-stage right shift adjustment strategy, comprising the steps of:
step 1, distributing each group of gypsum slurry on a corresponding machine according to a machine distribution strategy, and calculating the starting and stopping time of the production process;
step 2, initializing a time window set;
step 3, checking the working procedures of each group of gypsum slurry and the planned time window in the corresponding processing machine according to the sequence and the stages, if the gypsum slurry needs to move to the right, turning to step 4, otherwise turning to step 5;
step 4, right shifting the corresponding procedure according to the right shifting adjustment rule;
step 5, adding the planned time window into a time window set of a corresponding machine, judging whether all procedures of all gypsum slurry are planned, if so, turning to step 6, otherwise turning to step 3;
and 6, returning the model trained by the RVM (Relevance Vector Machine, related vector machine) and ending.
Further, in the second generation non-dominant ranking genetic algorithm, its fitness function is expressed as:
the gene operation method adopts a partial matching crossing mode, and the mutation mode comprises exchange mutation and reverse sequence mutation;
the genetic selection strategy adopts an elite retention strategy and a crowding degree to carry out selection operation, wherein the crowding degree is reflected by a mode of calculating crowding distance between adjacent individuals. The crowding distance refers to the sum of the length and width of a rectangle formed by interconnecting individuals adjacent to the target individual.
Assuming that the number of individuals in the non-dominant solution set is x, the individuals are denoted as O i ，O i If the crowding distance of the device is P (i) and the number of the objective functions is y, the P (i) is calculated by adopting the following formula:
wherein f y (. Cndot.) represents the objective function in the non-dominant solution set.
After the parent chromosome generates offspring through genetic manipulation, the algorithm mixes the parent and offspring to generate a mixed population G with the size of 2n t And calculate G t And (3) carrying out rapid non-dominant sorting to obtain a non-dominant solution set. Due to G t The number of internal individuals is2n, and the selected next generation population P t The size is n, so that selection is needed according to elite retention policy, i.e. the non-dominant solution set is put into P t Is a kind of medium. If the i-th level non-dominant solution set is put into P t After that, P t The number of internal individuals is still smaller than n, then the number of internal individuals is required to be equal to G t Is placed in P by selecting individuals in the i+1st non-dominant solution set t An inner part; if the i-th level non-dominant solution set is put into P t After that, P t If the number of individuals in the tree is greater than n, the i+1st non-dominant solution set is ordered according to the degree of congestion, and the individuals with large degree of congestion are put into P t Inner until P t The number of individuals in the cell reaches n.
Further, in the second generation non-dominant ranking genetic algorithm, the multi-objective decision method is as follows:
setting an objective function f 1 The maximum and minimum of (2) are f respectively 1max And f 1min Objective function f 2 The maximum and minimum of (2) are f respectively 2max And f 2min The method comprises the steps of carrying out a first treatment on the surface of the If f is satisfied 1max -f 1min ≥f 2max -f 2min Output f 1 Is the minimum of (2); if f is satisfied 1max -f 1min ＜f 2max -f 2min Output f 2 Is a minimum of (2).
In the invention, the NSGA-II algorithm has the following operation processes: solutions meeting constraints in the population are called feasible solutions, and the solution set consisting of all the feasible solutions is called feasible solution set and is marked as X Ω . Assuming m objective functions, X Ω There are two possible solutions x, y that satisfy:
then x is said to dominate y. And for an unfeasible solution set X Ω Any one of the feasible solutions x p This is called Pareto optimal solution. One set of all Pareto optimal solutions, referred to as the Pareto optimal solution set, may be defined as:
and inputting a plurality of groups of gypsum thick plate parameters, and solving the production beats of the novel gypsum thick plate production system according to the production beat control algorithm flow based on NSGA-II through an NSGA-II genetic algorithm.
The invention has the beneficial effects that: according to the invention, an objective function and constraint conditions are set for the production takt optimization model according to actual demands, then, the NSGA-II algorithm is adopted to optimize the production takt, and a priority-based machine allocation strategy and a time window-based multi-stage right shift adjustment strategy are used for decoding, so that a scheduling scheme capable of simultaneously optimizing the maximum finishing time and the total demoulding and delay is obtained, the yield of the novel gypsum thick plate production system is improved, the total demoulding and delay time can be effectively optimized along with the change of production proportion, and the failure rate of the system is reduced.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objects and other advantages of the invention may be realized and obtained by means of the instrumentalities and combinations particularly pointed out in the specification.
Drawings
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in the following preferred detail with reference to the accompanying drawings, in which:
FIG. 1 is a flowchart of a NSGA-II based tact control algorithm;
FIG. 2 is a flow chart of a gypsum board production process;
FIG. 3 is a line site layout;
FIG. 4 is a pareto non-dominant front;
FIG. 5 is a graph of minimum iteration of maximum dead time within a population;
fig. 6 is a graph of minimum iteration of total demold drag within a population.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the illustrations provided in the following embodiments merely illustrate the basic idea of the present invention by way of illustration, and the following embodiments and features in the embodiments may be combined with each other without conflict.
According to the invention, an objective function and constraint conditions are set for the production takt optimization model according to actual demands, the NSGA-II algorithm is adopted to optimize the production takt, and a machine allocation strategy based on priority and a multi-stage right shift adjustment strategy based on a time window are used for decoding, so that a scheduling scheme capable of simultaneously optimizing the maximum finishing time and the total demoulding and delay is obtained.
The method comprises the following steps:
1) And (3) making proper assumption on the actual production process of the novel gypsum thick plate, establishing a mathematical model of the production process including a start period, a production period and an end period, namely a production takt model, and obtaining an objective function for minimizing the maximum finishing time and the total demoulding delay time.
2) Solving the production takt control problem of the novel gypsum thick plate production system by using an NSGA-II algorithm, wherein the production takt control problem comprises the steps of selecting a proper coding mode, a decoding mode, a fitness function, a gene operation method, a genetic selection strategy and a multi-objective decision method.
For step 1), it includes:
(1) firstly, the following constraint is made on the complex novel gypsum thick plate production process:
the weights of the weighed gypsum, cement and water are known, and the environmental temperature of a production workshop is not greatly changed;
the priority of each group of gypsum thick plates is the same;
the production process comprises stirring, pouring, transferring in an initial setting area, initial setting forming and demoulding;
all machines are available in the initial state, but there is priority; specifically, in the stirring and pouring process, the four stirring tanks are sequentially a stirring tank 1, a stirring tank 3, a stirring tank 2 and a stirring tank 4 from high to low in priority;
no faults occur in the production process, and the production cannot be interrupted after the start.
(2) The following mathematical model is built according to the above constraints:
there are n groups of gypsum thick plate raw materials which are weighed in advance, the raw materials need to be produced through m working procedures, o (j) machines are arranged on the j th working procedure, p mould trolleys are arranged on each conveying line, and the processing time of each group of gypsum thick plates on part of working procedures needs to be predicted through a relevant vector machine (Relevance Vector Machine, RVM);
in the initial setting forming process, a plurality of groups of mould trolleys can be simultaneously initially set, and the first-in first-out principle is satisfied; in other working procedures, one production machine can only process one group of thick gypsum boards at the same time, and the starting condition of the transfer system turnover in the initial setting area is that the next pouring is finished, the demolding is finished and no turnover is carried out between the other transport line and the return line;
the mass matrix of gypsum board stock to be produced is represented as follows:
wherein M is sgn M snn And M wn Respectively representing the weights of gypsum, cement and water in the weighed gypsum raw materials, and each column of vectors represents a group of gypsum raw materials;
the hydration reaction time vector for the gypsum board of group a is shown below:
T a ＝[T jba ,T gza ,T cna ] T
wherein T is a Represents a hydration reaction time vector, a=1, 2, …, n, T jba 、T gza And T cna Respectively representing the stirring, pouring and setting removal time of the gypsum thick plate of the group a;
for any set of gypsum slabs production sequence pi= [ pi (1), pi (2), …, pi (n)]Setting S ij Indicating the start time, O, of the jth process of the ith set of gypsum slabs ij Indicating the processing time, E ij Indicating the end time, Z i The mold release downtime of the gypsum board is shown, D (pi (i), pi (i ')) is the start production interval of two adjacent gypsum boards, i' is the serial number of the next gypsum board of the i-th gypsum board.
To better describe the model, the gypsum board manufacturing process is divided into three stages: a start-up phase, a production phase, and an end phase, wherein the agitation and perfusion apparatus operates in the start-up phase and the production phase, the transfer system apparatus operates in the start-up phase, the production phase, and the end phase, and the demolding apparatus operates in the production phase and the end phase.
The conditions during the start-up period are:
1≤i≤2p+2
wherein, p represents that p mould trolleys are arranged on each transport line; in the stirring and pouring process, the maximum processing time interval between the ith group of gypsum thick plates and the ith' group of gypsum thick plates in the same stirring tank is as follows:
production start time S of the ith set of gypsum slabs i1 The formula is as follows:
S i1 ＝S (i-1)1 +D(π(i),π(i′))
the conditions during the production period are:
the demolding process start time is expressed as:
wherein T is cni Representation, t 2 Indicating the time during the turnaround that demolding is allowed to begin;
the mold release hold-off time is expressed as:
the starting conditions of the transfer system turnover procedure in the initial setting zone are represented by the following formula:
S i2 ＝max{S (i-2p-2)4, S (i-1)2 }
the maximum processing time interval between the i-th set of gypsum planks and the i' -th set of gypsum planks is determined under the condition that the conditions of the starting period and the production period are satisfied:
calculating the starting time and the pulling time of the demoulding process in the end period by adopting a fixed time interval mode, namely, the demoulding starting time depends on the initial setting time or the time of starting demoulding of a group of gypsum thick plates, and the time for one-time operation of a transfer system is assumed to be t sum The demolding start time and demolding delay time are as follows:
S i4 ＝max(S (i-1)4 +t 1 ,T cni )+t sum
(3) determining constraint conditions and objective functions:
definition of decision variable X ijk A 0-1 decision variable, 1 if the i-th set of gypsum slabs are arranged on the k-th processing machine at the j-th process step, or 0 otherwise;
definition of decision variable Y ijk1 A decision variable of 0-1, 1 if the ith set of gypsum slabs is arranged on the jth process in the ith process order on the kth processing machine, or 0 otherwise;
the constraint relationship is obtained as follows:
S i(j+1) ＝S ij +O ij ,j＝1,2,3
E ij ＝S ij +O ij
wherein B is ij Indicating the start time.
The objective function to minimize the maximum finishing time is:
f 1 ＝min(C max (π))
the objective function to minimize the total demold hold time is:
for step 2), it comprises:
(1) firstly, selecting a coding and decoding mode:
the coding mode adopts integer coding, the quantity of gypsum thick plates to be produced is set to be chromosome length, and population individuals are described by pi= [ pi (1), pi (2), … and pi (n) ].
In order to solve the machine allocation problem and the hydration reaction timing uninterrupted problem, the multi-stage right shift adjustment decoding strategy based on priority machine allocation and time window is used for decoding, and the steps are as follows:
step 1, distributing each group of gypsum slurry on a corresponding machine according to a machine distribution strategy, and calculating the starting and stopping time of the production process;
step 2, initializing a time window set;
step 3, checking the working procedures of each group of gypsum slurry and the planned time window in the corresponding processing machine according to the sequence and the stages, if the gypsum slurry needs to move to the right, turning to step 4, otherwise turning to step 5;
step 4, right shifting the corresponding procedure according to the right shifting adjustment rule;
step 5, adding the planned time window into a time window set of a corresponding machine, judging whether all procedures of all gypsum slurry are planned, if so, turning to step 6, otherwise turning to step 3;
and 6, returning to the model trained by the RVM, and ending.
(2) Setting a fitness function:
the fitness functions that minimize the maximum finishing time and minimize the total demold hold time are:
(3) selection gene manipulation method: the mutation mode comprises exchange mutation and reverse sequence mutation by adopting a partial matching crossing mode.
(4) Determining a genetic selection strategy:
the selection operation is performed using an elite retention policy and a degree of congestion, wherein the degree of congestion is reflected in a manner of calculating a congestion distance between adjacent individuals. The crowding distance refers to the sum of the length and width of a rectangle formed by interconnecting individuals adjacent to the target individual.
Assuming that the number of individuals in the non-dominant solution set is x, the individuals are denoted as O i ，O i If the crowding distance of the device is P (i) and the number of the objective functions is y, the P (i) is calculated by adopting the following formula:
wherein f y (. Cndot.) represents the objective function in the non-dominant solution set.
After the parent chromosome generates offspring through genetic manipulation, the algorithm mixes the parent and offspring to generate a mixed population G with the size of 2n t And calculate G t And (3) carrying out rapid non-dominant sorting to obtain a non-dominant solution set. Due to G t The number of individuals in the population P is 2n, and the next generation population P is selected t The size is n, so that selection is needed according to elite retention policy, i.e. the non-dominant solution set is put into P t Is a kind of medium. If the i-th level non-dominant solution set is put into P t After that, P t The number of internal individuals is still smaller than n, then the number of internal individuals is required to be equal to G t Is placed in P by selecting individuals in the i+1st non-dominant solution set t An inner part; if the i-th level non-dominant solution set is put into P t After that, P t If the number of individuals in the tree is greater than n, the i+1st non-dominant solution set is ordered according to the degree of congestion, and the individuals with large degree of congestion are put into P t Inner until P t The number of individuals in the cell reaches n.
(5) Selecting a multi-objective decision method:
the present invention selects the optimal solution in the non-dominant solution set according to the following rules:
assuming an objective function f in a non-dominant solution set 1 The maximum and minimum of (2) are f respectively 1max And f 1max Objective function f 2 The maximum and minimum of (2) are f respectively 2max And f 2min The method comprises the steps of carrying out a first treatment on the surface of the If f is satisfied 1max -f 1min ≥f 2max -f 2min Output f 1 Is the minimum of (2); if f is satisfied 1max -f 1min ＜f 2max -f 2min Output f 2 Is a minimum of (2).
In this embodiment, the present invention is applied to optimize the production process based on the existing production process of the thick gypsum board as shown in fig. 2, and the production line of the thick gypsum board as shown in fig. 3.
The embodiment of the invention is to produce a plurality of groups of thick gypsum plates with different specifications, wherein the environment temperature is 30 ℃, the weight of gypsum in a formula 1 is 190kg, the weight of cement is 52kg, the weight of water is 77kg, the weight of gypsum in a formula 2 is 210kg, the weight of cement is 45kg, and the weight of water is 72kg. The experimental simulation is to weigh part of the raw materials of the gypsum slurry in the actual production process in a certain day, the environmental temperature is 30 ℃, the number of the gypsum thick plates in the production formula 1 is 20, and the number of the gypsum thick plates in the production formula 2 is 20.
The implementation flow of the invention is shown in fig. 1, specifically: inputting a plurality of groups of gypsum thick plate parameters, and carrying out soft measurement on the stirring time, the pouring time and the initial setting time of the gypsum slurry by using an RVM model to obtain hydration reaction time of each stage of each group of gypsum thick plates.
The fitness function is set as follows:
an initial population P (1) with the size of n is randomly generated, the iteration times m=1 are set, the P (1) is subjected to cross mutation, a partial matching cross mode is selected, mutation and reverse sequence mutation are exchanged, and a first offspring C (1) is generated. And merging the parent population P (m) and the offspring population C (m) to generate a mixed population G (m). And (3) performing rapid non-dominant ranking, calculating the degree of congestion, sending the non-dominant solution set to an external population library, updating the external population library, and deleting the dominant solution. A new parent population P (m+1) is generated. m=m+1, and carrying out cross mutation on P (m) to generate a new offspring C (m), and carrying out loop iteration until reaching a termination condition, and outputting an external population pool.
The Pareto solution obtained by the algorithm is shown in fig. 4, and the minimum values of the two objective functions in each generation of population are shown in fig. 5 and 6. And selecting the maximum finishing time and the total demoulding delay time according to the minimum iteration value to obtain the novel gypsum thick plate beat control scheme.
After the proportion of the formula 1 and the formula 2 is changed, compared with the traditional fixed production takt mode, the maximum finishing time obtained by the invention has little change, but the total delay time has great change, so that the total demolding delay time is effectively optimized, and the failure rate of the system is reduced.
Finally, it is noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made thereto without departing from the spirit and scope of the present invention, which is intended to be covered by the claims of the present invention.
Claims (9)
1. A novel gypsum thick plate production beat control method is characterized in that: according to the method, a production process mathematical model, namely a production takt model, is established according to the production process of the novel gypsum thick plate, and an objective function and constraint conditions of minimizing the maximum finishing time and the total demolding delay time of the production takt model are set; and optimizing the production beats by adopting a second generation non-dominant sorting genetic algorithm, and decoding by using a priority-based machine allocation strategy and a multi-stage right shift adjustment strategy based on a time window to obtain a scheduling scheme capable of simultaneously optimizing the maximum finishing time and the total demolding delay.
2. The control method according to claim 1, characterized in that: the production process constraint of the novel gypsum thick plate is as follows:
the weights of the weighed gypsum, cement and water are known, and the environmental temperature of a production workshop is not greatly changed;
the priority of each group of gypsum thick plates is the same;
the production process comprises stirring, pouring, transferring in an initial setting area, initial setting forming and demoulding;
all machines are available in the initial state, but there is priority;
no faults occur in the production process, and the production cannot be interrupted after the start.
3. The control method according to claim 1, characterized in that: the takt model is as follows:
there are n groups of gypsum thick plate raw materials which are weighed in advance, the raw materials need to be produced through m working procedures, o (j) machines are arranged on the j th working procedure, p mould trolleys are arranged on each conveying line, and the processing time of each group of gypsum thick plates on part of working procedures needs to be predicted through a relevant vector machine;
in the initial setting forming process, a plurality of groups of mould trolleys can be simultaneously initially set, and the first-in first-out principle is satisfied; in other working procedures, one production machine can only process one group of thick gypsum boards at the same time, and the starting condition of the transfer system turnover in the initial setting area is that the next pouring is finished, the demolding is finished and no turnover is carried out between the other transport line and the return line;
the mass matrix of gypsum board stock to be produced is represented as follows:
wherein M is sgn 、M snn And M wn Respectively representing the weights of gypsum, cement and water in the weighed gypsum raw materials, and each column of vectors represents a group of gypsum raw materials;
the hydration reaction time vector for the gypsum board of group a is shown below:
T a ＝[T jba ,T gza ,T cna ] T
wherein T is a Represents a hydration reaction time vector, a=1, 2, …, n, T jba 、T gza And T cna Respectively representing the stirring, pouring and initial setting time of the gypsum thick plate of the group a;
for any set of gypsum slabs production sequence pi= [ pi (1), pi (2), …, pi (n)]Setting S ij Indicating the start time, O, of the jth process of the ith set of gypsum slabs ij Indicating the processing time, E ij Indicating the end time, Z i Indicating the time to release the gypsum board from the mold and D (pi (i), pi (i')) indicating the start of two adjacent sets of gypsum boardsThe production interval, i', represents the serial number of the next set of gypsum boards of the i-th set of gypsum boards.
4. The control method according to claim 1, characterized in that: according to the production takt model, the production process of the gypsum thick plate is divided into a starting period, a production period and an ending period; in the production process, the stirring and pouring equipment operates in a starting period and a production period, the transfer system equipment operates in the starting period, the production period and the end period, and the demolding equipment operates in the production period and the end period.
5. The control method according to claim 4, characterized in that: determining objective functions and constraints that minimize maximum finishing time and minimize total demold hold time from the production process, as follows:
the conditions during the start-up period are:
1≤i≤2p+2
wherein, p represents that p mould trolleys are arranged on each transport line; in the stirring and pouring process, the maximum processing time interval between the ith group of gypsum thick plates and the ith' group of gypsum thick plates in the same stirring tank is as follows:
production start time S of the ith set of gypsum slabs i1 The formula is as follows:
S i1 ＝S (i-1)1 +D(π(i),π(i′))
the conditions during the production period are:
2p+3≤i≤n
the demolding process start time is expressed as:
S i4 ＝max{S (i+2p+2)2 +t 2 ,T cni }
wherein T is cni Representation, t 2 Indicating the time during the turnaround that demolding is allowed to begin;
the mold release hold-off time is expressed as:
the starting conditions of the transfer system turnover procedure in the initial setting zone are represented by the following formula:
S i2 ＝max{S (i-2p-2)4 ,S (i-1)2 }
the maximum processing time interval between the i-th set of gypsum planks and the i' -th set of gypsum planks is determined under the condition that the conditions of the starting period and the production period are satisfied:
calculating the starting time and the pulling time of the demoulding process in the end period by adopting a fixed time interval mode, namely, the demoulding starting time depends on the initial setting time or the time of starting demoulding of a group of gypsum thick plates, and the time for one-time operation of a transfer system is assumed to be t sum The demolding start time and demolding delay time are as follows:
S i4 ＝max(S (i-1)4 +t 1 ,T cni )+t sum
definition of decision variable X ijk A 0-1 decision variable, 1 if the i-th set of gypsum slabs are arranged on the k-th processing machine at the j-th process step, or 0 otherwise;
definition of decision variable Y ijk1 A decision variable of 0-1, 1 if the ith set of gypsum slabs is arranged on the jth process in the ith process order on the kth processing machine, or 0 otherwise;
the constraint relationship is obtained as follows:
S i(j+1) ＝S ij +O ij ,j＝1,2,3
E ij ＝S ij +O ij
wherein B is ij Indicating a start time;
the objective function to minimize the maximum finishing time is:
f 1 ＝min(C max (π))
the objective function to minimize the total demold hold time is:
6. the control method according to claim 1, characterized in that: in the second generation non-dominant sorting genetic algorithm, the coding mode adopts integer coding, the quantity of gypsum thick plates to be produced is set to be chromosome length, and population individuals are described by pi= [ pi (1), pi (2), … and pi (n) ].
7. The control method according to claim 1, characterized in that: in the second generation non-dominant ranking genetic algorithm, decoding is performed by using a priority-based machine allocation strategy and a multi-stage right shift adjustment strategy based on a time window, and the method comprises the following steps of:
step 1, distributing each group of gypsum slurry on a corresponding machine according to a machine distribution strategy, and calculating the starting and stopping time of the production process;
step 2, initializing a time window set;
step 3, checking the working procedures of each group of gypsum slurry and the planned time window in the corresponding processing machine according to the sequence and the stages, if the gypsum slurry needs to move to the right, turning to step 4, otherwise turning to step 5;
step 4, right shifting the corresponding procedure according to the right shifting adjustment rule;
step 5, adding the planned time window into a time window set of a corresponding machine, judging whether all procedures of all gypsum slurry are planned, if so, turning to step 6, otherwise turning to step 3;
and 6, returning to the model trained by the relevant vector machine, and ending.
8. The control method according to claim 1, characterized in that: in the second-generation non-dominant ranking genetic algorithm, the fitness function is expressed as:
the gene operation method adopts a partial matching crossing mode, and the mutation mode comprises exchange mutation and reverse sequence mutation;
the genetic selection strategy adopts an elite retention strategy and a crowding degree to carry out selection operation, wherein the crowding degree is reflected by a mode of calculating crowding distance between adjacent individuals.
9. The control method according to claim 1, characterized in that: in the second generation non-dominant ordering genetic algorithm, the multi-objective decision method is as follows:
setting an objective function f 1 The maximum and minimum of (2) are f respectively 1max And f 1min Objective function f 2 The maximum and minimum of (2) are f respectively 2max And f 2min The method comprises the steps of carrying out a first treatment on the surface of the If f is satisfied 1max -f 1min ≥f 2max -f 2min Output f 1 Is the minimum of (2); if f is satisfied 1max -f 1min ＜f 2max -f 2min Output f 2 Is a minimum of (2).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310665383.3A CN116681248A (en) | 2023-06-06 | 2023-06-06 | Novel gypsum thick plate production beat control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310665383.3A CN116681248A (en) | 2023-06-06 | 2023-06-06 | Novel gypsum thick plate production beat control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116681248A true CN116681248A (en) | 2023-09-01 |
Family
ID=87778683
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310665383.3A Pending CN116681248A (en) | 2023-06-06 | 2023-06-06 | Novel gypsum thick plate production beat control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116681248A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117162225A (en) * | 2023-11-03 | 2023-12-05 | 江苏神禹港务工程有限公司 | Demoulding and forming method and system for concrete prefabricated part |
-
2023
- 2023-06-06 CN CN202310665383.3A patent/CN116681248A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117162225A (en) * | 2023-11-03 | 2023-12-05 | 江苏神禹港务工程有限公司 | Demoulding and forming method and system for concrete prefabricated part |
| CN117162225B (en) * | 2023-11-03 | 2024-02-23 | 江苏神禹港务工程有限公司 | Demoulding and forming method and system for concrete prefabricated part |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116681248A (en) | Novel gypsum thick plate production beat control method | |
| CN106779220B (en) | Steelmaking-continuous casting-hot rolling integrated scheduling method and system | |
| Ko et al. | GA-based decision support systems for precast production planning | |
| CN102266927B (en) | Control method for molten-steel casting sequence of continuous casting machine | |
| Long et al. | Scheduling a realistic hybrid flow shop with stage skipping and adjustable processing time in steel plants | |
| CN102346882B (en) | Bilayer planning method for intelligent scheduling for steelmaking-continuous welding production | |
| CN1885328B (en) | Steelmaking-continuous casting tundish batch plan method and system | |
| CN112699524B (en) | Simulation optimization scheduling model applied to special steel factory high-speed tool steel steelmaking process | |
| CN108303958B (en) | A kind of multi-objective flexible dispatching method of steel-making continuous casting process | |
| CN111563336A (en) | Deadlock-free scheduling method of flexible manufacturing system based on improved genetic algorithm | |
| CN115204497A (en) | Prefabricated part production scheduling optimization method and system based on reinforcement learning | |
| CN106227163B (en) | Equipment manufacturing system no-dead-time control method based on Petri network and simulated annealing | |
| CN112508398B (en) | Dynamic production scheduling method and device based on deep reinforcement learning and electronic equipment | |
| US11638952B2 (en) | Steelmaking-and-continuous-casting dispatching method and apparatus based on distributed robust chance-constraint model | |
| CN103778466B (en) | Converter steel-making temperature modeling forecasting method based on vector error and system thereof | |
| Wang et al. | Minimizing tardiness and makespan for distributed heterogeneous unrelated parallel machine scheduling by knowledge and Pareto-based memetic algorithm | |
| CN101591730B (en) | Method and device for improving operating efficiency of material handling equipment of bell type furnace units of steel enterprises | |
| CN104122861B (en) | The conflict resolution method lax based on the waiting time and Optimization Scheduling | |
| CN100394417C (en) | Regular scheduling method with state and performance feedback and its scheduling system | |
| CN114282370A (en) | Disassembly line setting method considering physical and mental loads of operator | |
| CN104942251B (en) | Cast-on time determining method of steel mill continuous casting machines | |
| CN112395690A (en) | Reinforced learning-based shipboard aircraft surface guarantee flow optimization method | |
| CN111062571B (en) | Ingot selection and batch-to-batch integration optimization method for aluminum industry | |
| CN105785963A (en) | Steelmaking and continuous casting scheduling method based on artificial bee colony (ABC) | |
| CN113139720A (en) | Casting shop production scheduling optimization method with learning effect |
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 |