Full-automatic packaging scheduling method based on multi-objective optimization algorithm

Abstract

A full-automatic packaging scheduling method based on a multi-objective optimization algorithm, which method relates to the technical field of intelligent production scheduling in packaging workshops. The method comprises: on the basis of work orders to be packaged of a production line, extracting production data of the production line, and initializing parameters; constructing a multi-objective optimization model of the packaging production line; to address the problems of premature convergence and susceptibility to local optima in an INSGA-II algorithm, using the INSGA-II algorithm to improve an initialization method, crossover and mutation strategies and crossover and mutation factors, and performing solving on the basis of objective functions such as minimizing the maximum makespan, minimizing the maximum energy consumption and minimizing the total machine load, so as to generate an optimized scheduling scheme; and starting packaging operations on the basis of the generated optimized scheduling scheme. The method can increase the unit-time production capacity of a production line, and effectively solve the problems in packaging production scheduling, thereby reducing the production costs of enterprises and improving the packaging production efficiency.

Description

Full-automatic packaging scheduling method based on multi-objective optimization algorithm TECHNICAL FIELD

[0001] The application belongs to the technical field of intelligent production scheduling of packaging workshops, and particularly relates to a full-automatic packaging scheduling method based on a multi-objective optimization algorithm. BACKGROUND

[0002] Product packaging plays an important role in chemical, manufacturing, medical, food and other industries, and the demand for packaging is increasing. Compared with traditional manual packaging production lines, automatic packaging production lines have the advantages of high efficiency, high packaging quality, high packaging flexibility, low production energy consumption and the like.

[0003] The automatic packaging scheduling system is an important link of production organization and management. Its essence is to introduce the function of management into the activities of work order production, material scheduling and material packaging, so as to coordinate the material configuration management and timely production of issued work orders in the workshop in a fast and effective manner.

[0004] However, the existing automatic packaging production line scheduling system has the defect of insufficient production resource scheduling. Due to the limited capacity of the production bin, the bin capacity saturation problem is easy to occur, which not only affects the production continuity, but also may cause shutdown processing and bring high cost loss. At the same time, the issued work order needs to be processed in time, and the complexity, dynamic randomness, multi-constraint and multi-objective of the packaging scheduling exist, which seriously affects the production continuity and production efficiency and increases the production cost. The scheduling method of the automatic packaging production line is the key to realize the scheduling system. The existing round-robin scheduling, priority scheduling, first-come-first-served scheduling and scheduling based on experience lack consideration of comprehensive factors, it is difficult to take into account the overall situation, the scheduling quality is poor and the efficiency is low. Therefore, in view of the above problems, the present application provides a full-automatic packaging scheduling method based on a multi-objective optimization algorithm.

[0005] SUMMARY

[0006] The application provides a full-automatic packaging scheduling method based on a multi-objective optimization algorithm. The scheduling system solves the problems in the background art by collecting full-process production information and scheduling information and solving the scheduling scheme by using the improved multi-objective optimization algorithm of INSGA-II.

[0007] To solve the above technical problems, the application is implemented by the following technical solutions:

[0008] The full-automatic packaging scheduling method based on a multi-objective optimization algorithm comprises an information management module, a real-time scheduling module and a production monitoring module.

[0009] The information management module manages the whole-process production information of the full-automatic packaging production line, and the whole-process production information includes production condition information, stockyard condition information and issued work order information of the full-automatic packaging production line; wherein the production condition information includes the number, name, power and packaging capacity of the packaging machine, the number, name, type and packaging requirement of the packaging material, the stockyard condition information includes the stockyard raw material category, current stock level, remaining material condition, water washing condition, warehouse capacity saturation condition and warehouse temperature and humidity, and the issued work order information includes the work order quantity, packaging requirement, material requirement and delivery time of the production work order, and the user can select different information management pages to browse the corresponding information and perform adding, modifying, deleting and querying operations on the related information.

[0010] The real-time scheduling module generates an optimized scheduling scheme based on a multi-objective optimization algorithm, arranges production feeding, packaging, water washing and other processes, and achieves the objectives of minimizing the maximum completion time, minimizing the maximum energy consumption and minimizing the total machine load, so as to optimize the scheduling scheme for the arrangement and issuance of the production task of the automatic production line.

[0011] The production monitoring module includes device operation condition, device energy consumption condition, work order execution condition and automatic production line abnormal condition detection; wherein the abnormal conditions include device failure, stockyard saturation, material shortage and work order conflict.

[0012] On the other hand, a full-automatic packaging scheduling method based on a multi-objective optimization algorithm is realized based on the foregoing full-automatic packaging scheduling system based on a multi-objective optimization algorithm, and specifically includes the following steps:

[0013] S1: According to the packaging work order of the production line, extracting the automatic production line production data and initializing the parameters;

[0014] S2: Constructing a multi-objective optimization model of the automatic packaging production line;

[0015] Wherein, the multi-objective optimization model establishment method is: the production system adopts multiple types of sensors to collect production scheduling data, obtains order information, packaging information, device information and resource information, transmits the data to the scheduling system through a communication protocol, and establishes a corresponding model;

[0016] Wherein, the multiple types of sensors include quality sensors, stock level sensors, temperature sensors, humidity sensors and pressure sensors; the order information includes order number, order priority, delivery time and order packaging requirement; the packaging information includes packaging scalar, packaging number and packaging model; the device information includes device operation condition, operation number, downtime number and maintenance number; and the resource information includes shift condition and material condition.

[0017] S3: Using improved non-dominated sorting genetic algorithm INSGA-Ⅱ, by minimizing the maximum completion time, minimizing the maximum energy consumption, minimizing the total load of the machine, and the objective function and constraint conditions, the packaging automation production line production scheduling is carried out, and the scheduling optimization scheme is generated;

[0018] S3.1: The objective function and constraint condition are established, and the mathematical expression is as follows: f1={c i |i=1,2,3...,n}; (1)

[0019] Wherein, f1 is the maximum completion time expression; wherein f2 is the maximum energy consumption expression; wherein f3 is the total load of the machine expression;

[0020] The objective function is as follows:

[0021] Wherein, F1, F2, F3 are the minimum maximum completion time, the minimum maximum energy consumption and the minimum total load of the machine optimization objective function;

[0022] Wherein, C i represents the packaging completion time of material i, and n is the total number of material work orders;

[0023] Q j represents the total energy consumption of equipment j in this packaging process;

[0024] CP j and IP j are the processing power and idle power of the packaging equipment j respectively; and are the packaging processing time and idle time of machine j respectively; Q is the total energy consumption of m machines;

[0025] Wherein,

[0026] T j represents the total packaging time of packaging equipment j.

[0027] The constraint condition is as follows:

[0028] a. The packaging equipment has spatial exclusivity when working;

[0029] b. The packaging process has spatial exclusivity, time exclusivity and time continuity when being carried out;

[0030] c. All packaging equipment starts at time 0;

[0031] d. The packaging order priority of different raw materials is the same at the beginning;

[0032] e. There is a precedence constraint between packaging processes of a certain raw material.

[0033] S3.2 Generate packaging process-based encoding and packaging equipment-based encoding.

[0034] S3.3 Start the algorithm, initialize the population P0, and use a hybrid initialization method. First, let the packaging process encoding part use the random initialization method, and then let the corresponding packaging equipment encoding part use the heuristic initialization for half and the random initialization for the other half.

[0035] Among them, the heuristic initialization is to select the optional equipment with the shortest concentrated processing time, and the random initialization is to randomly select.

[0036] S3.4 Determine whether the hierarchical sorting is completed. If not, perform non-dominated sorting and calculate the relevant crowding degree; if yes, set the initial generation number to 1;

[0037] Among them, the non-dominated sorting is to select individuals with high domination level into the offspring population, and if the domination level is the same, select individuals with small crowding degree; finally, constantly repeat the selection operation until the size of the new population reaches the size of the initial population.

[0038] S3.5 Decode the parent population solution and select the chromosome with the best fitness to retain;

[0039] S3.6 Perform crossover and mutation operations, and judge;

[0040] Among them, the fitness function is:

[0041] The above optimization objective function is to minimize the maximum completion time, minimize the maximum energy consumption, and minimize the total load of the machine.

[0042] NSGA-II is a fast non-dominated sorting multi-objective optimization algorithm, which has the advantages of fast running speed and good convergence of solution set, but has the problems of premature convergence and easy falling into local optimum. The INSGA-II algorithm is improved by improving the initialization method, crossover and mutation operation, and crossover and mutation factor.

[0043] The crossover operation: adopt uniform crossover method, set the sub-packaging set G1, cross the packaging process encoding based on the process priority order, and a part of the offspring is inherited from the same part of the parent 1 and G1 genes, and the other part is replaced by the different genes of the parent 2 and G1;

[0044] The mutation operation: individual gene allelic exchange is performed between the parents and offspring that are not in genetic relationship;

[0045] The mutation factor:

[0046] The crossover factor:

[0047] Wherein, Gen is the population iteration number;

[0048] ρ c (i) and ρ m (i) is the value of the crossover factor and the mutation factor in the ith iteration, And is the maximum and minimum value of the crossover factor, and the parameters are 0.75 and 0.35; And is the maximum and minimum value of the mutation factor, and the parameters are 0.12 and 0.0012;

[0049] S3.7 obtains the offspring population P1, performs population merging, and after merging, is sorted according to the non-dominated order, the crowding degree is calculated, and the generation number is generation number+1;

[0050] S3.8 judges whether the iteration number reaches the maximum iteration number, if the condition is met, the cycle is ended, otherwise, go to S3.4;

[0051] S3.9 the algorithm is run, and the optimization scheduling scheme of the packaging production line is formulated according to the solving parameters.

[0052] S4: according to the optimization scheduling scheme generated in the S3 step, start the packaging work;

[0053] S5: according to the actual execution situation, update the parameters, and optimize the scheduling scheme again until the packaging processing is finished.

[0054] The present application has the following beneficial effects compared with the prior art:

[0055] (1) The present application takes the automatic packaging production line scheduling as the main research object, and researches around the optimization scheduling method, solves in the minimum maximum completion time, the minimum maximum energy consumption, the minimum machine total load and other objective functions by adopting the improved non-dominated sorting genetic algorithm INSGA-II, generates the optimization scheduling scheme, and starts the packaging work according to the generated optimization scheduling scheme;

[0056] (2) The present application can increase the unit time capacity of the automatic packaging production line, effectively solve the packaging production scheduling problem, and further save the production cost of the enterprise, reduce the energy consumption, and improve the packaging production efficiency.

[0057] Of course, any product implementing the present application does not necessarily need to achieve all the advantages described above at the same time. BRIEF DESCRIPTION OF DRAWINGS

[0058] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort based on these drawings.

[0059] Fig. 1 is a schematic diagram of a full-automatic packaging scheduling system module based on a multi-objective optimization algorithm according to the present application;

[0060] Fig. 2 is a schematic diagram of a flow of a full-automatic packaging scheduling method based on a multi-objective optimization algorithm according to the present application.

[0061] Fig. 3 is a flowchart of an improved non-dominated sorting genetic algorithm INSGA-II of a full-automatic packaging scheduling method based on a multi-objective optimization algorithm according to the present application. DETAILED DESCRIPTION

[0062] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort fall within the scope of the present application.

[0063] As shown in Fig. 1, a full-automatic packaging scheduling system module based on a multi-objective optimization algorithm according to the present application comprises an information management module, a real-time scheduling module and a production monitoring module.

[0064] Specifically, the information management module manages the full-process production information of the full-automatic packaging production line, which includes production situation information, stockyard situation information and issued work order information of the full-automatic packaging production line. The production situation information includes the number, name, power and packaging capacity of the packaging machine, the number, name, type and packaging requirement of the packaging material, etc. The stockyard situation information includes the stockyard raw material category, current stock level, remaining material situation, washing situation, storage capacity saturation situation, storage temperature and humidity, etc. The issued work order information includes the number of production work orders, packaging requirements, material requirements, delivery time, etc. The user can select different information management pages to browse the corresponding information, and perform adding, modifying, deleting and querying operations on the related information.

[0065] Specifically, the real-time scheduling module generates an optimized scheduling scheme based on a multi-objective optimization algorithm, arranges the production feeding, packaging, washing and other processes, and achieves the objectives of minimizing the maximum completion time, minimizing the maximum energy consumption, minimizing the total machine load, etc. The optimized scheduling scheme is used for the arrangement and issuance of the production tasks of the automatic production line.

[0066] Specifically, the production monitoring module includes equipment operation, equipment energy consumption, work order execution, and automated production line abnormality detection; wherein the abnormality includes equipment failure, bin saturation, material shortage, and work order conflict.

[0067] As shown in Figure 2, the full-automatic packaging scheduling method based on the multi-objective optimization algorithm of the application comprises:

[0068] S1: according to the production line packaging work order, extracting the automated packaging production line production data and initializing the parameters;

[0069] S2: constructing a multi-objective optimization model of the automated packaging production line;

[0070] Specifically, the multi-objective optimization model establishment method is: the production system adopts multiple sensors to collect production scheduling data, obtains order information, packaging information, equipment information, and resource information, and transmits the data to the scheduling system through a communication protocol to establish a corresponding data model;

[0071] Among them, the multiple sensors include quality sensors, level sensors, temperature sensors, humidity sensors, and pressure sensors; the order information includes order number, order priority, delivery time, and order packaging demand; the packaging information includes packaging scalar, packaging number, and packaging model; the equipment information includes equipment running status, running number, downtime number, and maintenance number; and the resource information includes shift situation and material situation.

[0072] S3: using the INSGA-II optimization algorithm, minimizing the maximum completion time, minimizing the maximum energy consumption, minimizing the total machine load, and the objective function and constraint conditions, to perform packaging automated production line production scheduling, and generate a scheduling optimization scheme;

[0073] S4: starting packaging work according to the optimization scheduling scheme generated in S3;

[0074] S5: updating the algorithm parameters according to the actual execution, re-optimizing the scheduling scheme, until the packaging process is completed.

[0075] As shown in Figure 3, the NSGA-II multi-objective optimization algorithm of the full-automatic packaging scheduling method based on the multi-objective optimization algorithm of the application comprises:

[0076] S3.1: establishing an objective function and constraint conditions;

[0077] S3.2 generating a code based on the packaging process and based on the packaging equipment;

[0078] S3.3 algorithm starts, initializes population P0, adopts hybrid initialization method, first let the packaging process coding part all use random initialization method, then let the corresponding packaging equipment coding part half use heuristic initialization, the other half uses random initialization;

[0079] S3.4 determines whether the hierarchical sorting is completed, if not, performs non-dominated sorting, and calculates the related crowding degree; if yes, sets the initial generation number as 1;

[0080] S3.5 decodes the parent population solution, and selects to reserve the best fitness chromosome;

[0081] S3.6 performs crossover and mutation operations, and judges;

[0082] S3.7 obtains the child population P1, performs population merging, and after merging, performs non-dominated order sorting, calculates the crowding degree, and sets the iteration number = generation number + 1;

[0083] S3.8 determines whether the iteration number reaches the maximum iteration number, if yes, the loop ends, if not, goes back to S3.4;

[0084] S3.9 algorithm runs completely, and formulates the packaging production line optimization scheduling scheme according to the solving parameters.

[0085] As a preferred scheme, the specific implementation form is as follows:

[0086] S3.1: the mathematical expressions of the objective function and the constraint condition are as follows: f1={c i |i=1,2,3...,n}; (1)

[0087] Specifically, f1 is the maximum completion time expression; f2 is the maximum energy consumption expression; and f3 is the total machine load expression.

[0088] The objective function is as follows:

[0089] Specifically, F1, F2 and F3 are the optimization objective functions of minimizing the maximum completion time, minimizing the maximum energy consumption and minimizing the total machine load.

[0090] Specifically, the constraint condition is:

[0091] a. the packaging equipment has spatial exclusivity when working;

[0092] b. the packaging process has spatial exclusivity, time exclusivity and time continuity when working;

[0093] c. all packaging equipment starts at time 0;

[0094] d. The initial packaging sequence priority of different raw materials is the same;

[0095] e. There is a constraint between the packaging processes of a certain raw material;

[0096] Specifically, C i represent the packaging completion time of material i, and n is the total number of material work orders;

[0097] Q j represents the total energy consumption of device j during this packaging process;

[0098] CP j and IP j are the processing power and idle power of packaging device j, respectively; and are the packaging processing time and idle time of machine j, respectively;

[0099] Specifically,

[0100] Q is the total energy consumption of m machines; T j represents the total packaging time of packaging device j.

[0101] S3.3: Heuristic initialization selects optional devices for packaging processes with the shortest centralized processing time, and random initialization randomly selects optional devices.

[0102] S3.4: Specifically, non-dominated sorting selects individuals with high dominance levels into the offspring population, and if the dominance levels are the same, individuals with small crowding degrees are selected. Finally, repeatedly extract selection operations until the size of the new population reaches the size of the initial population.

[0103] S3.5: The fitness function is:

[0104] to minimize the maximum completion time, minimize the maximum energy consumption, and minimize the total load of the machine optimization objective function.

[0105] To solve the problem of premature convergence and easy to fall into local optimum of NSGA-II algorithm, INSGA-II algorithm improves the initialization method, crossover and mutation operation, crossover and mutation factor.

[0106] Specifically, the crossover operation adopts uniform crossover, sets a sub-packaging set G1, and the packaging process code is crossed based on the process priority order. Part of the offspring is inherited from the same part of the parent 1 and G1 genes, and the other part is replaced by the different genes of the parent 2 and G1;

[0107] Specifically, the variation operation performs individual gene allelic exchange between the parents and the offspring in non-genetic relationship for the packaging process coding;

[0108] Variation factor:

[0109] Crossover factor:

[0110] Specifically, Gen is the number of population iterations;

[0111] ρ c (i) and ρ m (i) is the value of the crossover factor and the variation factor in the i-th iteration, and are the maximum and minimum values of the crossover factor, and the parameters are set to 0.75 and 0.35; and are the maximum and minimum values of the variation factor, and the parameters are set to 0.12 and 0.0012.

[0112] The preferred embodiments of the application disclosed above are only used to help explain the application. The preferred embodiments do not describe all the details and limit the application to the specific embodiments described. Obviously, many modifications and changes can be made according to the content of the specification. The specification selects and describes these embodiments in order to better explain the principles and practical applications of the application, so that those skilled in the art can well understand and utilize the application. The application is limited only by the claims and their entire scope and equivalents.

Claims

1. A fully automatic packaging scheduling method based on a multi-objective optimization algorithm, characterized in that, It comprises the following steps: S1, according to the production line to be packaged work order, extract the automation packaging production line production data and initialize parameters; S2: build an automated packaging production line multi-objective optimization model; The multi-objective optimization model building method is: the production system adopts multiple sensors to collect production scheduling data, obtains order information, packaging information, equipment information and resource information, and transmits the data to the scheduling system through the communication protocol to establish the corresponding data model; The multiple sensors include quality sensors, level sensors, temperature sensors, humidity sensors, pressure sensors; the order information includes order number, order priority, delivery time, and order packaging demand; the packaging information includes packaging quantity, packaging number, and packaging model; the equipment information includes equipment running status, running number, downtime number, and maintenance number; and the resource information includes shift situation and material situation; S3: using INSGA-II optimization algorithm, through minimizing the maximum completion time, minimizing the maximum energy consumption, minimizing the total machine load, and target function and constraint conditions, the packaging automation production line production scheduling is carried out, and the scheduling optimization scheme is generated; S4: according to the optimization scheduling scheme generated in step S3, the packaging work is started; S5: according to the actual execution situation, the algorithm parameters are updated, the scheduling scheme is re-optimized, and the packaging processing is ended.

2. The fully automatic packaging scheduling method based on multi-objective optimization algorithm according to claim 1, characterized in that, The INSGA-II optimization algorithm in the S3 step is realized through the following steps: S3.1: establishing the target function and constraint conditions; S3.2 generating coding based on packaging process and based on packaging equipment; S3.3 starting the algorithm, initializing the population P0, using a mixed initialization method, first using a random initialization method for the packaging process coding part, then using a heuristic initialization for half of the corresponding packaging equipment coding part and using a random initialization for the other half; S3.4 judging whether the hierarchical sorting is completed, if not, performing non-dominated sorting and calculating the relevant crowding degree; if yes, setting the initial iteration number as 1; S3.5 decoding the parent population, and selecting the best fitness chromosome to be reserved; S3.6 performing crossover and mutation operations, and judging; S3.7 obtaining the child population P1, performing population merging, sorting according to the non-dominated order after merging, calculating the crowding degree, and letting the iteration number = iteration number + 1; S3.8 judging whether the iteration number reaches the maximum iteration number, if yes, the loop is ended, otherwise, returning to step S3.4; S3.9 the algorithm is run, and the packaging production line optimization scheduling scheme is formulated according to the solving parameters.

3. The fully automatic packaging scheduling method based on multi-objective optimization algorithm according to claim 2, characterized in that, The specific content of the S3.1 step is: The mathematical expressions of the target function and constraint conditions are as follows: f1 = {c i |i = 1, 2, 3..., n}; (1) Specifically, f1 is the maximum completion time expression; f2 is the maximum energy consumption expression; and f3 is the total machine load expression. Specifically, F1, F2 and F3 are the optimization target functions of minimizing the maximum completion time, minimizing the maximum energy consumption and minimizing the total machine load; The objective function is as follows: Specifically, the constraint conditions are: a. the packaging equipment has spatial exclusivity when working; b. the packaging process has spatial exclusivity, time exclusivity and time continuity when working; c. all packaging equipment starts at time 0. ​ d. The initial different raw materials have the same priority of packaging sequence; e. There is a constraint between the packaging processes of a certain raw material; In particular, C i representing the packaging completion time of the material i, n is the total number of material work orders; Q j represents the total energy consumption of the device j during this packaging process; CP j and IP j are, respectively, the processing power and the idle power of the packaging apparatus j; and respectively, the packaging processing time and the idle time of the machine j; In particular, Q is the sum of the energy consumed by m machines; T j represents the total packaging time of the packaging apparatus j.

4. The fully automatic packaging scheduling method based on multi-objective optimization algorithm according to claim 2, characterized in that, In the S3.3 step, the heuristic initialization is to select the optional equipment with the shortest centralized processing time, and the random initialization is to randomly select.

5. The fully automatic packaging scheduling method based on multi-objective optimization algorithm according to claim 2, characterized in that, In the S3.4 step, the non-dominated sorting is to select the individuals with high domination level into the offspring population, and if the domination levels are the same, the individuals with small crowding degree are selected; finally, the selection operation is repeatedly extracted until the size of the new population reaches the size of the initial population.

6. The fully automatic packaging scheduling method based on multi-objective optimization algorithm according to claim 2, characterized in that, In the S3.5 step, the fitness is calculated by the following fitness function: The fitness function is: The optimization objective function is to minimize the maximum completion time, minimize the maximum energy consumption, and minimize the total load of the machine.

7. The fully automatic packaging scheduling method based on multi-objective optimization algorithm according to claim 2, characterized in that, The S3.6 step is specifically: To solve the problems of premature convergence and easy falling into local optimum of the NSGA-II algorithm, the INSGA-II algorithm improves the initialization method, the crossover and mutation operation, and the crossover and mutation factors; The crossover operation adopts the uniform crossover mode, sets the sub-packaging set G1, and the packaging process coding is crossed based on the process priority order; a part of the offspring is genetically inherited from the same part of the parent 1 and G1, and the other part is replaced by the different genes of the parent 2 and G1; Specifically, the mutation operation performs individual gene allelic exchange between the parents and offspring that are not in a genetic relationship; Variation factor: Crossing factor: Specifically, Gen is the number of population iterations; p c (i) and p m (i) is the value of the crossover factor and the mutation factor in the i-th iteration, and For the cross-factor maximum and minimum, the parameters are set to 0.75 and 0.35; and The maximum and minimum values of the mutation factor are 0.12 and 0.0012.

8. The fully automatic packaging scheduling method based on multi-objective optimization algorithm according to claim 1, characterized in that, The full-automatic packaging scheduling method is realized based on a full-automatic packaging scheduling system, and the full-automatic packaging scheduling system includes an information management module, a real-time scheduling module, and a production monitoring module; The information management module manages the full-process production information of the full-automatic packaging production line, and the full-process production information includes production situation information, stockyard situation information, and issued work order information of the full-automatic packaging production line; the production situation information includes the number, name, power, and packaging capacity of the packaging machine, and the number, name, type, and packaging requirements of the packaging material; the stockyard situation information includes the stockyard raw material category, current stock level, remaining material situation, water washing situation, warehouse capacity saturation situation, and storage temperature and humidity; the issued work order information includes the number of production work orders, packaging requirements, material requirements, and delivery time; the user selects different information management pages to browse the corresponding information, and performs addition, modification, deletion, and query operations on the related information; The real-time scheduling module generates an optimized scheduling scheme based on a multi-objective optimization algorithm, arranges the processes of production feeding, packaging, and water washing, and achieves the objectives of minimizing the maximum completion time, minimizing the maximum energy consumption, and minimizing the total load of the machine The optimized scheduling scheme is used for the arrangement and issuance of the production tasks of the automatic production line; The production monitoring module includes equipment operation situation, equipment energy consumption situation, work order execution situation, and automatic production line abnormal situation detection; The abnormal situations include equipment failure, stockyard saturation, material shortage, and work order conflict.

Images