Cabinet selection method based on improved genetics algorithm for cut tobacco production workshop

Abstract

The invention discloses an improved genetics algorithm-based cabinet selection method for a cut tobacco production workshop. The method comprises the following steps of: initialization: initializing data in a strategy algorithm; acquiring information: acquiring current work order information; obtaining selectable stations: obtaining currently selectable station information; selecting an available station from the selectable stations by utilizing a genetic strategy; and feeding back a selection result. According to the improved genetics algorithm-based cabinet selection method for the tobacco shred making workshop, the current cabinet selection mode is optimized, a reasonable cabinet selection strategy is designed, the production time is reduced as much as possible under the condition that the occupation times of all cabinets are close, and it is ensured that the cabinet selection path in each day is the shortest path and the production time is the shortest; the production time can be shortened, the standby time of equipment is shortened, the use efficiency of the equipment is improved, and unmanned production can be realized in combination with a current batch automatic circulation system.

Description

Technical Field

[0001] The invention relates to the technical field of cigarette manufacturing, and more specifically to a cabinet selection method based on an improved genetic algorithm for a tobacco-making workshop. Background Art

[0002] The production of the silk-making workshop is a typical flow workshop operation mode. A production line is composed of different process production equipment. Each equipment completes a fixed process, mass production, discrete storage, and the sections are connected by storage cabinets to form an organic whole of production. The production line is composed of series and parallel modes, which to a certain extent forms a mixed flow workshop with flexible production. The materials go through a series of processes from the raw material warehouse to unpacking and enter the pre-distribution cabinet. After that, the cabinet enters the leaf storage cabinet after a secondary feeding process. After a fixed leaf storage time, the cabinet enters the shredding. The whole process goes through two in and out of the cabinet process.

[0003] The speed at which the material moves on the belt is fixed, but the distance from each cabinet is not the same. The time difference between the farthest cabinet and the nearest cabinet in the discharge of the first material or the feed of the last material may be as much as ten minutes.

[0004] Therefore, there is an urgent need for a cabinet selection method based on an improved genetic algorithm for use in a silk workshop. Summary of the invention

[0005] The purpose of the present invention is to provide a cabinet selection method based on an improved genetic algorithm for a silk-making workshop to solve the problems in the above-mentioned prior art, shorten the production time, reduce the equipment standby time, and increase the equipment utilization efficiency. In addition, it can be combined with the current batch automatic flow system to realize unmanned production.

[0006] The present invention provides a cabinet selection method based on an improved genetic algorithm for a silk workshop, which comprises:

[0007] Step S1, initialization: initializing the data in the strategy algorithm;

[0008] Step S2, obtaining information: obtaining current work order information;

[0009] Step S3, obtaining optional workstations: obtaining the information of currently selectable workstations;

[0010] Step S4, selecting an available workstation from the optional workstations using a genetic strategy;

[0011] Step S5: provide feedback on the selection result.

[0012] As described above, the cabinet selection method based on the improved genetic algorithm for the silk-making workshop, wherein, preferably, in the step S3, the step of obtaining the optional workstations, the rules for the optional workstations include: the cabinet is not occupied; the cloth traveling motor of the cabinet is in a normal state; the cabinet is not marked as disabled; the cabinet cannot be successfully selected after the initial cabinet selection.

[0013] As described above, the cabinet selection method based on improved genetic algorithm for a silk-making workshop, wherein preferably, the step S4, selecting an available workstation from the optional workstations by using genetic strategy, specifically includes:

[0014] Step S41, encoding, selecting binary encoding mode for encoding;

[0015] Step S42, initializing the population, using the improved circle method to initialize the population;

[0016] Step S43, fitness calculation;

[0017] Step S44: determine whether to perform the catastrophic algorithm according to the fitness calculation result, if yes, execute step S45, if no, execute step S46;

[0018] Step S45, perform a disaster operation, and after the disaster operation is completed, execute step S46;

[0019] Step S46: selection;

[0020] Step S47, cross;

[0021] Step S48, mutation;

[0022] Step S49, determine whether the condition is met, if so, end, if not, return to step S43.

[0023] As described above, the cabinet selection method based on the improved genetic algorithm for the silk-making workshop, wherein preferably, the step S42, initializing the population, uses the improved circle method to initialize the population, specifically including: calculating the Euclidean distance between any two points and adding them, then reversing all positions between the two points to confirm whether the route length becomes shorter, otherwise proceeding to the next operation.

[0024] As described above, the cabinet selection method based on improved genetic algorithm for a silk-making workshop, wherein preferably, the step S43, fitness calculation, specifically includes:

[0025] When the goal is to minimize the maximum completion time, the quotient of the function difference is selected for calculation.

[0026] As described above, the cabinet selection method based on the improved genetic algorithm for the silk-making workshop, wherein, preferably, the step S44, judging whether to perform the catastrophic algorithm according to the calculation result of the fitness, specifically includes:

[0027] Step S441, set the first generation population as the initial population, retain the population as the best catastrophic population and save its best individual as the best catastrophic individual, and then perform genetic operations. When iterating to the i-th generation population, confirm that it is within the catastrophic cutoff generation number N×m and is the set catastrophic operation generation number, and enter step S442, otherwise continue to perform genetic operations;

[0028] Step S442: Determine the fitness of the global optimum in the current population and the retained catastrophic best individual, retain the population with the best fitness, and update the best individual;

[0029] Step S443: Initialize the first pop individuals in the evolutionary population after fitness sorting, and then perform genetic operations on the newly initialized population.

[0030] As described above, the cabinet selection method based on improved genetic algorithm for a silk-making workshop, wherein preferably, the step S45, performing a catastrophic operation, specifically includes:

[0031] Step S451: Perform an adaptive crossover operation during the disaster cycle using the following formula:

[0032]

[0033] Among them, Pc represents the crossover probability, Num represents the number of disasters currently occurring, K1 is a constant value less than 1, and K2 is used to adjust the range of crossover probability;

[0034] Step S452: Perform an adaptive mutation operation during the disaster cycle using the following formula:

[0035]

[0036]

[0037] Among them, Pm represents the mutation probability, w is N times of m, and N is the total number of catastrophes. When V>i≥w, the mutation probability is adaptively calculated and no catastrophe operation is performed. After w generations of genetic operations are performed, the replaced population will continue to perform V-w generations of genetic operations to adaptively adjust the mutation probability. V is the actual total number of iterations, and K4 is used to adjust the range of crossover probability.

[0038] The cabinet selection method based on the improved genetic algorithm for the silk reeling workshop as described above, wherein, preferably, the step S46, selection, specifically includes:

[0039] Adopt the roulette wheel strategy for selection, specifically including:

[0040] Calculate the fitness of each chromosome, and calculate the ratio P(i) of the fitness value of each chromosome in the total fitness respectively;

[0041] Calculate the cumulative fitness ratio of the chromosome, q(i);

[0042] If rand < q(1), then select individual 1, otherwise select individual k that satisfies q(k - 1) < rand ≤ q(k), and repeat this operation N times.

[0043] The cabinet selection method based on the improved genetic algorithm for the silk reeling workshop as described above, wherein, preferably, the step S47, crossover, specifically includes:

[0044] Select a single-point crossover operator for calculation, specifically including: randomly set only one crossover point in the individual coding string, divide the chromosome into two parts, and the left and right sides of the offspring chromosome come from the parent chromosomes respectively.

[0045] The cabinet selection method based on the improved genetic algorithm for the silk reeling workshop as described above, wherein, preferably, the step S48, mutation, specifically includes:

[0046] Perform mutation operation through the adaptive mutation method, and calculate the mutation probability through the following formula :

[0047]

[0048] Wherein, represents the fitness of the current individual; (0 ≤ ≤ 1) represents the mutation probability adjustment parameter.

[0049] The invention provides a cabinet selection method based on an improved genetic algorithm for a silk-making workshop. On the basis of the existing workshop, the cabinet selection measurement of the improved genetic algorithm is added to replace the current manual sequential decision. The algorithm uses the improved circle method to initialize the population on the basis of the genetic algorithm, introduces a disaster operation to avoid a local optimal solution, uses a roulette wheel for selection, selects a binary-coded crossover method in a crossover method, and selects an adaptive mutation in a mutation method. The current cabinet selection method is optimized, and a reasonable cabinet selection strategy is designed to ensure that the production time is reduced as much as possible when the number of occupancy of each cabinet is similar, and ensure that the cabinet selection path of each day is in the shortest path and the production time is the shortest. The production time can be shortened, the equipment standby time can be reduced, and the equipment utilization efficiency can be increased. In addition, the current batch automatic flow system can be combined to realize unmanned production. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described below with reference to the accompanying drawings, in which:

[0051] Figure 1 The hybrid flow shop model described in the present invention;

[0052] Figure 2 A flow chart of an embodiment of a cabinet selection method based on an improved genetic algorithm for a silk-making workshop provided by the present invention;

[0053] Figure 3 This is a schematic diagram of the algorithm operation flow described in the present invention;

[0054] Figure 4 This is a schematic diagram of the algorithm crossover algorithm described in the present invention, namely, chromosome single-point crossover. DETAILED DESCRIPTION

[0055] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. The description of the exemplary embodiments is merely illustrative and is in no way intended to limit the present disclosure and its application or use. The present disclosure can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to make the present disclosure thorough and complete and to fully express the scope of the present disclosure to those skilled in the art. It should be noted that unless otherwise specifically stated, the relative arrangement of the components and steps, the composition of the materials, the numerical expressions and the numerical values ​​set forth in these embodiments should be interpreted as being merely exemplary and not as limiting.

[0056] The words "first", "second" and similar words used in this disclosure do not indicate any order, quantity or importance, but are only used to distinguish different parts. The words "include" or "comprises" and similar words mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of including other elements. "Up", "down" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0057] In the present disclosure, when a specific component is described as being located between a first component and a second component, there may or may not be an intermediate component between the specific component and the first component or the second component. When a specific component is described as being connected to other components, the specific component may be directly connected to the other components without an intermediate component, or may not be directly connected to the other components but have an intermediate component.

[0058] All terms (including technical terms or scientific terms) used in the present disclosure have the same meanings as those understood by ordinary technicians in the field to which the present disclosure belongs, unless otherwise specifically defined. It should also be understood that terms defined in general dictionaries, such as general dictionaries, should be interpreted as having meanings consistent with their meanings in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined herein.

[0059] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0060] Figure 1 The mixed flow workshop model is shown, with multiple (for example, 4) pre-distribution cabinets between the primary feeding section and the secondary feeding section, and multiple (for example, 5) leaf storage cabinets between the secondary feeding section and the shredding section. The speed at which the material moves on the belt is fixed, but the distance from each cabinet is different. The time difference between the farthest cabinet and the nearest cabinet in the discharge of the head material or the feeding of the tail material may be up to ten minutes. In order to shorten the time in and out of the cabinet as much as possible, reduce the batch production time and thus reduce the standby time of the equipment, reduce energy waste, and improve the efficiency of equipment use, it is very important to select cabinets reasonably.

[0061] In order to study the scheduling problem of mixed-flow workshop, the following four assumptions are given: 1) In the flow workshop, only the processing of tobacco is considered; 2) Before production, the equipment in the workshop is ready and there is no material on the production line; 3) The processing time includes preparation time and transportation time; 4) There are process constraints between the same brands in the workshop.

[0062] like Figure 2As shown, the cabinet selection method based on the improved genetic algorithm for a silk-making workshop provided in this embodiment includes the following steps in actual execution:

[0063] Step S1, initialization: Initialize the data in the strategy algorithm.

[0064] Step S2, obtain information: obtain current work order information.

[0065] Exemplarily, confirming the production data confirms the single / double cabinet selection.

[0066] Step S3, obtaining optional workstations: obtaining the information of currently selectable workstations.

[0067] Specifically, the rules for selecting workstations include: the cabinet is not occupied; the fabric traveling motor of the cabinet is in normal state; the cabinet is not marked as disabled; and the cabinet cannot be successfully selected after the first cabinet selection.

[0068] Step S4: Select an available workstation from the optional workstations using a genetic strategy.

[0069] like Figure 3 As shown, in one embodiment of the cabinet selection method based on the improved genetic algorithm for a silk-making workshop of the present invention, the step S4 may specifically include:

[0070] Step S41: Encoding: Select binary encoding for encoding.

[0071] Since binary encoding is simple and complies with the minimum character set encoding principle, the present invention selects binary encoding for encoding.

[0072] Step S42: Initialize the population using the improved circle method.

[0073] Although the improved circle algorithm has a weak search randomness and cannot obtain the global optimal solution, it can be used to initialize the population better so that other algorithms can be used to solve the problem later. Therefore, the present invention uses the improved circle method to initialize the population. Specifically, the Euclidean distance between any two points is calculated and added to obtain C ij , then reverse all the positions between the two points to confirm whether the route length becomes shorter, otherwise proceed to the next operation;

[0074] .

[0075] Step S43: Fitness calculation.

[0076] Specifically, when the goal is to minimize the maximum completion time, the quotient of the function difference is selected for calculation, rather than simply using the reciprocal of the function value for calculation;

[0077] Assume OV(i) is the value of the i-th chromosome, OVmax and OVmin represent the maximum and minimum values ​​respectively, and the fitness F(i) of the i-th chromosome is expressed as:

[0078] .

[0079] Step S44: determine whether to perform the catastrophic algorithm based on the fitness calculation result. If yes, execute step S45; if not, execute step S46.

[0080] In one embodiment of the cabinet selection method based on improved genetic algorithm for a silk-making workshop of the present invention, the step S44 may specifically include:

[0081] Step S441, set the first generation population as the initial population, retain the population as the best catastrophe population and save its best individual as the best catastrophe individual, and then perform genetic operations. When iterating to the i-th generation population, confirm that it is within the catastrophe cutoff generation N×m and is the set catastrophe operation generation, and enter step S442, otherwise continue with the genetic operation.

[0082] Step S442: Determine the fitness of the global optimum in the current population and the retained catastrophic best individual, retain the population with the best fitness, and update the best individual.

[0083] Step S443: Initialize the first pop individuals in the evolutionary population after fitness sorting, and then perform genetic operations on the newly initialized population.

[0084] Step S45, perform a disaster operation, and execute step S46 after the disaster operation is completed.

[0085] In some implementations of the present invention, the step S45, performing a disaster operation, specifically includes:

[0086] Step S451: Perform an adaptive crossover operation during the disaster cycle using the following formula:

[0087]

[0088] Among them, Pc represents the crossover probability, Num represents the number of disasters currently occurring, K1 is a constant value less than 1, and K2 is used to adjust the range of variation of the crossover probability.

[0089] The above formula can improve the global search capability of population mutation.

[0090] Step S452: Perform an adaptive mutation operation during the disaster cycle using the following formula:

[0091]

[0092]

[0093] Among them, Pm represents the mutation probability, w is N times of m, and N is the total number of catastrophes. When V > i ≥ w, the mutation probability is calculated adaptively, and the catastrophe operation is no longer performed. After w generations of genetic operations are executed, the replaced population continues to execute V - w generations of genetic operations to adaptively adjust the mutation probability. V is the actual total number of iterations, and K4 is used to adjust the change range of the crossover probability.

[0094] In the later stage of the genetic operation, the population converges to a high degree. To enhance the search ability of the population at this time, the present invention adaptively adjusts the mutation probability within the catastrophe cycle, so that the diversity of the genes of the population after the catastrophe is enriched and the mutation probability is increased.

[0095] Step S46, Selection.

[0096] By the selection operation, the inferior chromosomes in the initialized population are eliminated and replaced with excellent chromosomes to further optimize the population. In the present invention, the roulette wheel strategy is adopted for selection. In an implementation manner of the cabinet selection method based on the improved genetic algorithm for the silk reeling workshop of the present invention, the step S46 may specifically include:

[0097] Step S461, Calculate the fitness of each chromosome, and calculate the ratio P(i) of the fitness value of each chromosome in the total fitness respectively.

[0098] Step S462, Calculate the cumulative fitness ratio q(i) of the chromosomes.

[0099] Step S463, If rand < q(1), then select individual 1, otherwise select individual k that satisfies q(k - 1) < rand ≤ q(k), and repeat this operation N times.

[0100] Step S47, Crossover.

[0101] The crossover of chromosomes is the process of mating two chromosomes with each other, exchanging and recombining their genes to form two new individuals. In the present invention, a single-point crossover operator is selected for calculation. Specifically, as Figure 4 shown, only a single crossover point is randomly set in the individual coding string, dividing the chromosome into two parts, and the left and right sides of the offspring chromosome come from the parent chromosomes respectively.

[0102] Step S48, Mutation.

[0103] The mutation operation is to perform appropriate mutation operations on the parts of the chromosomes after the crossover, so as to increase the diversity of the population and prevent the excellent individuals from being destroyed. In the present invention, the mutation operation is performed by an adaptive mutation method. This method introduces the number of iterations g and combines the chromosome mutation probability with the fitness. Specifically, the mutation probability is calculated by the following formula: :

[0104]

[0105] in, Represents the current individual fitness; (0≤ ≤1) indicates the mutation probability adjustment parameter

[0106] Step S49, determine whether the condition is met, if so, end, if not, return to step S43.

[0107] Step S5: provide feedback on the selection result.

[0108] Specifically, after the calculated cabinet selection result is transmitted to the PLC (Programmable Logic Controller), the PLC cabinet selection point is read to determine whether the cabinet for which the result is given has been selected, otherwise the result is re-output. If the result selection cannot be confirmed twice, the cabinet corresponding to the result is defined as a non-selectable cabinet, and the cabinet selection algorithm operation is performed again.

[0109] The cabinet selection method based on the improved genetic algorithm for a silk-making workshop provided in an embodiment of the present invention adds a cabinet selection measurement of the improved genetic algorithm to the existing basis of the workshop to replace the current manual sequential decision-making; the algorithm uses the improved circle method to initialize the population on the basis of the genetic algorithm, and introduces a disaster operation to avoid local optimal solutions, uses a roulette wheel for selection, selects a binary-coded crossover method in the crossover method, and selects an adaptive mutation in the mutation method; optimizes the current cabinet selection method, and designs a reasonable cabinet selection strategy to ensure that the production time is reduced as much as possible when the number of occupancy of each cabinet is similar, and ensures that the cabinet selection path of each day is in the shortest path and the production time is the shortest; it can shorten the production time, reduce the equipment standby time, and increase the equipment utilization efficiency. In addition, it can be combined with the current batch automatic flow system to realize unmanned production.

[0110] So far, various embodiments of the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0111] Although some specific embodiments of the present disclosure have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified or some technical features may be replaced by equivalents without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A cabinet selection method based on improved genetic algorithm for a silk workshop, characterized in that: include: Step S1, initialization: initializing the data in the strategy algorithm; Step S2, obtaining information: obtaining current work order information; Step S3, obtaining optional workstations: obtaining the information of currently selectable workstations; Step S4, selecting an available workstation from the optional workstations using a genetic strategy; Step S5: provide feedback on the selection result.

2. The cabinet selection method based on improved genetic algorithm for silk-making workshop according to claim 1 is characterized in that: In the step S3, the step of obtaining optional workstations, the rules for optional workstations include: the cabinet is not occupied; the cloth traveling motor of the cabinet is in normal state; the cabinet is not marked as disabled; and the cabinet cannot be successfully selected after the first cabinet selection.

3. The cabinet selection method based on improved genetic algorithm for silk-making workshop according to claim 1 is characterized in that: The step S4, selecting an available workstation from the optional workstations by using a genetic strategy, specifically includes: Step S41, encoding, selecting binary encoding mode for encoding; Step S42, initializing the population, using the improved circle method to initialize the population; Step S43, fitness calculation; Step S44: determine whether to perform the catastrophic algorithm according to the fitness calculation result, if yes, execute step S45, if no, execute step S46; Step S45, perform a disaster operation, and after the disaster operation is completed, execute step S46; Step S46: selection; Step S47, cross; Step S48, mutation; Step S49, determine whether the condition is met, if so, end, if not, return to step S43.

4. The cabinet selection method based on improved genetic algorithm for a silk-making workshop according to claim 3 is characterized in that: The step S42, initializing the population, uses the improved circle method to initialize the population, specifically including: calculating the Euclidean distance between any two points and adding them, then reversing all positions between the two points to confirm whether the route length becomes shorter, otherwise proceeding to the next operation.

5. The cabinet selection method based on improved genetic algorithm for silk-making workshop according to claim 3 is characterized in that: The step S43, fitness calculation, specifically includes: When the goal is to minimize the maximum completion time, the quotient of the function difference is selected for calculation.

6. The cabinet selection method based on improved genetic algorithm for a silk-making workshop according to claim 3 is characterized in that: The step S44, judging whether to perform the catastrophic algorithm according to the fitness calculation result, specifically includes: Step S441, set the first generation population as the initial population, retain the population as the best catastrophic population and save its best individual as the best catastrophic individual, and then perform genetic operations. When iterating to the i-th generation population, confirm that it is within the catastrophic cutoff generation number N×m and is the set catastrophic operation generation number, and enter step S442, otherwise continue to perform genetic operations; Step S442: Determine the fitness of the global optimum in the current population and the retained catastrophic best individual, retain the population with the best fitness, and update the best individual; Step S443: Initialize the first pop individuals in the evolutionary population after fitness sorting, and then perform genetic operations on the newly initialized population.

7. The cabinet selection method based on improved genetic algorithm for a silk-making workshop according to claim 3 is characterized in that: The step S45, performing a disaster operation, specifically includes: Step S451: Perform an adaptive crossover operation during the disaster cycle using the following formula: Among them, Pc represents the crossover probability, Num represents the number of disasters currently occurring, K1 is a constant value less than 1, and K2 is used to adjust the range of crossover probability; Step S452: Perform adaptive mutation operation in the disaster cycle using the following formula: Among them, Pm represents the mutation probability, w is N times of m, and N is the total number of catastrophes. When V > i ≥ w, the mutation probability is calculated adaptively and the catastrophe operation is no longer performed. After w generations of genetic operations are executed, the replaced population continues to execute V - w generations of genetic operations to adaptively adjust the mutation probability. V is the actual total number of iterations, and K4 is used to adjust the change range of the crossover probability.

8. The cabinet selection method based on improved genetic algorithm for a silk-making workshop according to claim 3 is characterized in that: The step S46, selection, specifically includes: Using the roulette wheel strategy for selection, specifically including: Calculating the fitness of each chromosome and respectively calculating the ratio P(i) of the fitness value of each chromosome in the total fitness; Calculating the cumulative fitness ratio of the chromosome, q(i); If rand < q(1), then select individual 1, otherwise select individual k that satisfies q(k - 1) < rand ≤ q(k), and repeat this operation N times.

9. The cabinet selection method based on improved genetic algorithm for a silk-making workshop according to claim 3 is characterized in that: The step S47, crossover, specifically includes: Selecting a single-point crossover operator for calculation, specifically including: randomly setting only one crossover point in the individual coding string, dividing the chromosome into two parts, and the left and right sides of the offspring chromosome come from the parent chromosomes respectively.

10. The cabinet selection method based on improved genetic algorithm for a silk-making workshop according to claim 3 is characterized in that: The step S48, mutation, specifically includes: The mutation operation is performed through adaptive mutation mode, and the mutation probability is calculated by the following formula : in, Represents the current individual fitness; (0≤ ≤1) represents the mutation probability adjustment parameter.

Images