Pharmaceutical process scheduling scheme optimization method and device for solid preparation workshop

Abstract

The application relates to the field of pharmaceutical scheduling, and particularly relates to a pharmaceutical process scheduling scheme optimization method for a solid preparation workshop, which comprises the following steps: obtaining production parameter information based on historical pharmaceutical information; establishing a pharmaceutical scheduling model based on the production parameter information and pharmaceutical process information, the pharmaceutical scheduling model being used for optimizing maximum completion time and pharmaceutical cost, the pharmaceutical process information comprising pharmaceutical batch process information and pharmaceutical equipment information; establishing a scheduling encoding and decoding model between the pharmaceutical batch process information and the pharmaceutical equipment information; and solving the pharmaceutical scheduling model and the scheduling encoding and decoding model to obtain a scheduling scheme, the scheduling scheme being an association relationship between the pharmaceutical process information and the pharmaceutical equipment information.

Description

Technical Field

[0001] This application relates to the field of pharmaceutical scheduling, specifically to a method, apparatus, electronic device, and non-transitory computer-readable storage medium for optimizing pharmaceutical process scheduling in a solid dosage form workshop. Background Technology

[0002] Pharmaceuticals are a national treasure of my country, passed down through generations and becoming an indispensable part of modern medicine. Currently, with the continuous development of science and technology, pharmaceutical manufacturing has entered a modern, centralized, and standardized production model. Solid dosage forms are the most commonly used drug formulations in the pharmaceutical industry, and the production efficiency of related workshops has a significant impact on the company's supply capacity and economic benefits. However, due to the continuous expansion of drug varieties and production scale, the production information for solid dosage forms is gradually exceeding the scope of manual processing, leading to frequent problems such as orders not being completed on time and reduced profits. Therefore, the pharmaceutical industry urgently needs a scheduling optimization method for solid dosage form workshops to improve the overall production efficiency of these workshops.

[0003] Pharmaceutical solid dosage form workshops typically comprise several production lines, each producing different processes. For example, a tablet production line requires tableting and coating, while a capsule production line requires filling. Furthermore, while modern workshops often have multiple machines or sets of equipment capable of completing the same process, to comply with GMP production standards and traceability requirements, each batch of drugs must ultimately be processed using only one machine or set of equipment. Once a process begins, the next process can only begin after the entire batch of that process is completed and the area is cleared. Therefore, solid dosage form production is characterized by multiple processes, flexibility, and numerous constraints.

[0004] Traditional scheduling theory always models problems within a deterministic environment. However, due to the complexity of pharmaceutical solid dosage form production, there are almost no production parameters in the workshop that can be given precise values. This leads to the poor performance of conventional scheduling methods in practical applications. Therefore, for such workshops, in addition to fully considering their production characteristics, it is also necessary to take into account the uncertainty of production data in order to propose more reliable and efficient scheduling methods. Summary of the Invention

[0005] To address the above issues, this application proposes a method, apparatus, electronic device, and non-transitory computer-readable storage medium for optimizing pharmaceutical process scheduling in solid dosage form workshops. Production parameter information is extracted from historical pharmaceutical information, and a pharmaceutical scheduling model is established using this production parameter information and pharmaceutical process information. Furthermore, a scheduling encoding and decoding model is established between pharmaceutical batch process information and pharmaceutical equipment information. Finally, the pharmaceutical scheduling model and the scheduling encoding and decoding model are optimized and solved to obtain an optimized scheduling scheme.

[0006] According to one aspect of this application, a method for optimizing pharmaceutical process scheduling in a solid dosage form workshop is proposed, comprising:

[0007] Production parameter information is obtained based on historical pharmaceutical information;

[0008] A pharmaceutical scheduling model is established based on the production parameter information and pharmaceutical process information. The pharmaceutical scheduling model is used to optimize the maximum completion time and pharmaceutical cost. The pharmaceutical process information includes pharmaceutical batch process information and pharmaceutical equipment information.

[0009] Establish a scheduling encoding and decoding model between the pharmaceutical batch process information and the pharmaceutical equipment information;

[0010] An optimized scheduling scheme is obtained by solving the pharmaceutical scheduling model and the scheduling encoding and decoding model. The scheduling scheme is the association between the pharmaceutical process information and the pharmaceutical equipment information.

[0011] Furthermore, the production parameter information obtained based on historical pharmaceutical information statistics includes:

[0012] The historical pharmaceutical information is cleaned to obtain the minimum, most likely, and maximum values ​​of single-process processing time, equipment operating cost, and pharmaceutical raw material cost.

[0013] Furthermore, the establishment of a pharmaceutical scheduling model based on the production parameter information and pharmaceutical process information includes:

[0014] Based on the minimum, most likely, and maximum values ​​of the single-process processing time, the equipment operating cost, and the pharmaceutical raw material cost, triangular fuzzy numbers are established for the single-process processing time, pharmaceutical raw material cost, and equipment operating cost, respectively.

[0015] Establish pharmaceutical constraint relationships based on the pharmaceutical batch process information and the pharmaceutical equipment information;

[0016] Based on the triangular fuzzy numbers of the single-process processing time, the cost of pharmaceutical raw materials, and the operating cost of equipment, objective functions for the maximum completion time and the cost of fuzzy pharmaceutical manufacturing are established.

[0017] Furthermore, establishing pharmaceutical constraint relationships based on the pharmaceutical batch process information and the pharmaceutical equipment information includes:

[0018]

[0019]

[0020]

[0021]

[0022]

[0023] Where n is the total number of pharmaceutical batches, m is the total number of pharmaceutical equipment, and u i x represents the total number of pharmaceutical processes involved in the i-th batch of drugs. ijk To determine whether the j-th process of the i-th batch of drugs should be produced on the pharmaceutical equipment numbered k, y ijkt To determine whether the j-th process of the i-th batch of medicine is produced on the pharmaceutical equipment numbered k at time t. and Let ξ be the fuzzy completion time of the j-th process of the i-th batch of drugs and the (j-1)-th process of the preceding i-th batch of drugs on the pharmaceutical equipment numbered k, where ξ is infinite. z represents the fuzzy start time of the qth process in the pth batch of drugs. ijpqk Should the q-th process of batch p and the j-th process of batch i both be produced using pharmaceutical equipment numbered k? Let be the fuzzy start time of the j-th process in the i-th batch of drugs on the pharmaceutical equipment numbered k. Let be the fuzzy production time of the j-th process in the i-th batch of drugs on the pharmaceutical equipment numbered k.

[0024] Furthermore, the objective function for establishing the maximum completion time and fuzzy pharmaceutical cost based on the triangular fuzzy number of the single-process processing time, the cost of the pharmaceutical raw materials, and the equipment operating cost includes:

[0025] Based on the triangular fuzzy number of the single-process completion time, an objective function for the maximum completion time of fuzzy pharmaceutical manufacturing is established:

[0026]

[0027] in, The fuzzy maximum completion time is... The fuzzy completion time represents the i-th batch of drugs. Let be the fuzzy completion time of the i-th process of the i-th batch of drugs on the pharmaceutical equipment numbered k;

[0028] A fuzzy pharmaceutical cost objective function is established based on the triangular fuzzy numbers of the pharmaceutical raw material costs and the equipment operating costs:

[0029]

[0030] in, For the aforementioned fuzzy pharmaceutical cost, Let be the fuzzy pharmaceutical raw material cost of the i-th batch of drugs; Let k be the fuzzy equipment operating cost of the pharmaceutical equipment.

[0031] Furthermore, establishing a scheduling encoding / decoding model between the pharmaceutical batch process information and the pharmaceutical equipment information includes:

[0032] The correspondence between the pharmaceutical batch process information and the pharmaceutical equipment information is constructed based on the pharmaceutical process priority coding and pharmaceutical equipment coding.

[0033] Furthermore, the step of solving the pharmaceutical scheduling model and the scheduling encoding / decoding model to obtain the optimized scheduling scheme includes:

[0034] An improved multi-objective quantum particle swarm optimization algorithm is used to optimize the pharmaceutical scheduling model and the scheduling encoding / decoding model to obtain an optimized scheduling scheme.

[0035] According to a second aspect of the present invention, a pharmaceutical process scheduling optimization device for a solid dosage form workshop is provided, comprising:

[0036] The parameter extraction module obtains production parameter information based on historical pharmaceutical information;

[0037] The scheduling modeling module establishes a pharmaceutical scheduling model based on the production parameter information and pharmaceutical process information. The pharmaceutical scheduling model is used to optimize the maximum completion time and pharmaceutical cost. The pharmaceutical process information includes pharmaceutical batch process information and pharmaceutical equipment information.

[0038] The coding modeling module establishes a scheduling encoding and decoding model between the pharmaceutical batch process information and the pharmaceutical equipment information.

[0039] The optimization module solves the pharmaceutical scheduling model and the scheduling encoding / decoding model to obtain an optimized scheduling scheme, which is the association between the pharmaceutical process information and the pharmaceutical equipment information.

[0040] According to a third aspect of the present invention, an electronic device is provided, comprising:

[0041] One or more processors;

[0042] Storage device for storing one or more programs;

[0043] When the one or more programs are executed by the one or more processors, the one or more processors perform the method described above.

[0044] According to a fourth aspect of the present invention, a non-transitory computer-readable storage medium is provided, having stored thereon computer-readable instructions that, when executed by a processor, cause the processor to perform the method described above.

[0045] The beneficial effects of the technical solution provided in this application are as follows:

[0046] According to some embodiments, this application fully considers the uncertainties of pharmaceutical solid dosage form workshops and designs a scheduling model for the workshop based on production parameter information and pharmaceutical process information, so that the final scheduling result has better reliability and risk resistance.

[0047] According to some embodiments, this application designs a pharmaceutical process scheduling optimization method for a solid dosage form workshop, which comprehensively considers the maximum completion time of production and pharmaceutical costs, and can greatly improve the production efficiency of the workshop. Attached Figure Description

[0048] Figure 1 A flowchart illustrating the pharmaceutical process scheduling optimization method for a solid dosage form workshop according to an embodiment of this application is shown.

[0049] Figure 2 This diagram illustrates a two-layer coding scheme for optimizing the pharmaceutical process scheduling in a solid dosage form workshop, as described in an embodiment of this application.

[0050] Figure 3 The flowchart illustrates the solution process of the improved multi-objective quantum particle swarm optimization algorithm for optimizing the pharmaceutical process scheduling scheme of a solid dosage form workshop according to an embodiment of this application.

[0051] Figure 4 This diagram illustrates the result of discrete mapping of the particle process portion of the pharmaceutical process scheduling optimization method for a solid dosage form workshop according to an embodiment of this application.

[0052] Figure 5 The Pareto front comparison diagram shows the simulation experiment of the pharmaceutical process scheduling optimization method of the solid dosage form workshop according to the embodiment of this application.

[0053] Figure 6 This diagram illustrates the results obtained by the IMOQPSO algorithm for optimizing the pharmaceutical process scheduling scheme of a solid dosage form workshop according to an embodiment of this application.

[0054] Figure 7 A block diagram of a pharmaceutical process scheduling optimization device for a solid dosage form workshop according to an embodiment of this application is shown.

[0055] Figure 8 A block diagram of an electronic device according to an exemplary embodiment is shown. Detailed Implementation

[0056] To make the objectives and technical implementation of this application clearer, the specific implementation methods of this application will be further described below with reference to the accompanying drawings and embodiments. The accompanying drawings constitute a part of this application and, together with the embodiments, are used to illustrate the implementation principles of this application, but are not limited to the application scenarios of this application.

[0057] This application provides an optimization method for pharmaceutical process scheduling in a solid dosage form workshop. First, it uses triangular fuzzy numbers to characterize production parameter information to adapt to the uncertainty of the production process and determines the pharmaceutical manufacturing process and equipment constraints, establishing a pharmaceutical scheduling model with fuzzy maximum completion time and fuzzy pharmaceutical cost as objective functions. Second, it designs an efficient scheduling encoding and decoding model for the pharmaceutical scheduling model, which is represented by a two-layer encoding, including the correspondence between pharmaceutical process priorities and pharmaceutical equipment. Finally, it proposes an advanced multi-objective improved quantum particle swarm optimization algorithm to solve the pharmaceutical scheduling model and the scheduling encoding and decoding model. The algorithm combines Pareto theory and uses the non-dominated solution set found during the search process as the output to provide diverse alternative solutions.

[0058] Figure 1 A flowchart illustrating the pharmaceutical process scheduling optimization method for a solid dosage form workshop according to an embodiment of this application is shown.

[0059] like Figure 1 As shown, in S101, production parameter information is obtained based on historical pharmaceutical information.

[0060] According to the example embodiment, historical pharmaceutical information is cleaned to obtain the minimum, most likely, and maximum values ​​of single-process processing time, equipment operating cost, and pharmaceutical raw material cost.

[0061] According to one embodiment, historical pharmaceutical information refers to historical pharmaceutical records, which include information such as drug batch number, raw material cost of the corresponding batch of drugs, pharmaceutical equipment number, processing time of pharmaceutical processes on the corresponding pharmaceutical equipment, and unit time operating cost of the pharmaceutical equipment.

[0062] The minimum, most likely, and maximum values ​​of single-process processing time, equipment operating cost, and pharmaceutical raw material cost are extracted from these values ​​to establish subsequent triangular fuzzy numbers, as detailed later.

[0063] In S103, a pharmaceutical scheduling model is established based on production parameter information and pharmaceutical process information.

[0064] According to the example implementation, firstly, based on the minimum, most likely, and maximum values ​​of single-process processing time, equipment operating cost, and pharmaceutical raw material cost, triangular fuzzy numbers for single-process processing time, pharmaceutical raw material cost, and equipment operating cost are established respectively.

[0065] Due to numerous uncertainties in pharmaceutical solid dosage form workshops, such as equipment wear and tear, unstable temperature control, and significant variations in raw material quality, production parameters cannot be precisely represented. Since using triangular fuzzy numbers to represent production parameters can fully reflect the uncertainties of the production process, and to ensure the computability of the mathematical model, triangular fuzzy numbers are used to quantify the concept of uncertainty, typically represented as... Its membership function is as follows:

[0066]

[0067] Here, t1, t2, and t3 represent three key points describing the characteristics of the triangular fuzzy number, with corresponding membership function values ​​of 0, 1, and 0, respectively. The membership function between the three points has a linear relationship. In actual scheduling, t1, t2, and t3 correspond to the minimum, most likely, and maximum values ​​of the production parameters they represent, specifically the minimum, most likely, and maximum values ​​of the single-process processing time, equipment operating cost, and pharmaceutical raw material cost.

[0068] Furthermore, when implementing specific scheduling, it is necessary to define the basic operations of triangular fuzzy numbers. In this embodiment, the completion time of the process and the cost of pharmaceutical manufacturing rely on addition and multiplication operations, while the start time of each process needs to be obtained by taking the larger of the completion times of the relevant preceding processes according to the constraints. The fuzzy maximum completion time in the objective is obtained through comparison operations. Let... and Given two arbitrary triangular fuzzy numbers, the specific operational rules are as follows:

[0069] Addition operation:

[0070] Multiplication operation:

[0071] Take the larger operation: when hour, otherwise

[0072] Comparison operation: Prioritize judgment like but like when judge like but like when judge like but like but In other cases, the two fuzzy numbers are considered equal.

[0073] According to the example implementation, it is also necessary to establish pharmaceutical constraint relationships based on pharmaceutical batch process information and pharmaceutical equipment information.

[0074] Analysis of the production model of a pharmaceutical solid dosage form workshop revealed that the workshop needs to consider the production of multiple batches of drugs on different pharmaceutical equipment. Each batch of drugs involves multiple processes, and the number of pharmaceutical processes and the available pharmaceutical equipment for each process vary between different drugs due to different pharmaceutical process routes. In order to comply with the relevant requirements of GMP (Good Manufacturing Practice), certain constraints must be followed during the production process, including: (1) any pharmaceutical process for each batch of drugs can only be completed on one pharmaceutical equipment from start to finish; (2) no single pharmaceutical equipment can be used for multiple pharmaceutical processes at the same time; (3) each batch of drugs must be produced according to a specific process flow, i.e., the pharmaceutical processes for the same batch of drugs need to be arranged in a certain sequence; (4) once the pharmaceutical equipment starts production, it cannot stop until the current pharmaceutical process is completed. Specifically:

[0075]

[0076]

[0077]

[0078]

[0079]

[0080] Where n is the total number of batches of pharmaceuticals produced in one scheduling cycle within the workshop; m is the total number of pharmaceutical equipment in the workshop; u i x represents the total number of pharmaceutical processes involved in the i-th batch of drugs; ijk For the j-th process of the i-th batch of drugs O ij Should we select pharmaceutical equipment M with the serial number k? k Production is represented by 1 if it is not 0; y ijkt For the j-th process of the i-th batch of drugs Oij Is the pharmaceutical equipment M, numbered k, at time t? k Production is represented by 1, not 0; and O represents the j-th process of the i-th batch of drugs. ij and the (j-1)th process of the i-th batch of drugs preceding it. i(j-1) In pharmaceutical equipment M numbered k k The fuzzy completion time on ξ; ξ is infinity, that is, an infinitely large number; For the qth process of the pth batch of drugs, O pq The fuzzy start time; z ijpqk For the qth process of the pth batch of drugs, O pq And the j-th process of the i-th batch of drugs O ij Should all pharmaceutical equipment M with the number k be selected? k Production, and O ij Prior to O pq , is 1, not 0; For the j-th process of the i-th batch of drugs O ij In pharmaceutical equipment M numbered k k The fuzzy start time on; For the j-th process of the i-th batch of drugs O ij In pharmaceutical equipment M numbered k k The required fuzzy production time.

[0081] The solution objectives of this invention include minimizing the fuzzy maximum completion time and the fuzzy pharmaceutical cost.

[0082] According to the example embodiment, an objective function for the maximum completion time and the cost of fuzzy pharmaceutical manufacturing is established based on the triangular fuzzy number of single-process processing time, pharmaceutical raw material cost and equipment operating cost.

[0083] According to the example embodiment, an objective function for the maximum completion time of fuzzy pharmaceutical manufacturing is established based on the triangular fuzzy number of the single-process completion time:

[0084]

[0085] in, To fuzzy the maximum completion time, The fuzzy completion time represents the i-th batch of drugs. Let be the fuzzy completion time of the i-th process of the i-th batch of drugs on the pharmaceutical equipment numbered k, and max{} represents taking the maximum value of the variable within the parentheses.

[0086] According to the example embodiment, a fuzzy pharmaceutical cost objective function is established based on the triangular fuzzy number of the pharmaceutical raw material cost and the equipment operating cost:

[0087]

[0088] in, For the aforementioned fuzzy pharmaceutical cost, Let be the fuzzy pharmaceutical raw material cost of the i-th batch of drugs; Let k be the fuzzy equipment operating cost of the pharmaceutical equipment.

[0089] In S105, a scheduling encoding and decoding model is established between pharmaceutical batch process information and pharmaceutical equipment information.

[0090] According to the example embodiment, a correspondence between pharmaceutical batch process information and pharmaceutical equipment information is constructed based on pharmaceutical process priority coding and pharmaceutical equipment coding.

[0091] According to one embodiment, the pharmaceutical batch process information is the numbering information of each pharmaceutical process for each batch of drugs.

[0092] According to one embodiment, the pharmaceutical equipment information is the serial number information of the pharmaceutical equipment.

[0093] Based on the proposed pharmaceutical scheduling model, the final solution is to allocate one pharmaceutical processing device to each pharmaceutical process for each batch of drugs, prioritize the pharmaceutical batch processes on each processing device, and determine the fuzzy start and end times of each pharmaceutical process, i.e., the scheduling scheme. To effectively optimize this complex process using algorithms, a suitable scheduling encoding / decoding model must be determined.

[0094] According to one embodiment, the encoding method is as follows:

[0095] The coding mechanism used is a two-layer coding system based on pharmaceutical batch process numbers and pharmaceutical equipment numbers. The first layer is the pharmaceutical batch process code (OS), which represents the production priority of all pharmaceutical processes for all pharmaceutical batches. It is a discrete sequence composed of drug batch numbers from 1 to n. The number of times each batch number appears in the code equals the total number of pharmaceutical processes for that batch of drug; the earlier the number appears, the higher the priority of the pharmaceutical process it represents. The second layer is the pharmaceutical equipment code (MS), which, from the first pharmaceutical process of the first batch number to the last pharmaceutical process of the last batch number, is a discrete sequence composed of pharmaceutical equipment numbers. The sequence length is the total number of pharmaceutical batch processes, thus establishing a one-to-one correspondence between manufacturing batch processes and manufacturing equipment. (Reference) Figure 2 The double-layer coding diagram shown above, as analyzed above, indicates that the priority order of the processes it describes is O. 31 →O 11 →O 12 →O 32 →O 21→O 13 →O 22 The corresponding devices are {M3,M1,M1,M1,M2,M3,M2}.

[0096] According to one embodiment, the decoding method is as follows:

[0097] When forming a scheduling scheme based on the above encoding, the specific decoding steps are as follows:

[0098] S1: Initialize counter c=1, and set the pharmaceutical process number of each batch of drugs to be processed to 1.

[0099] S2: Extract the element with index c in the pharmaceutical process part of the code, and record the batch number i represented by the element.

[0100] S3: Obtain the upcoming pharmaceutical manufacturing process for batch number i. ij And retrieve the corresponding pharmaceutical equipment M by searching the pharmaceutical equipment code. k .

[0101] S4: Comparison of pharmaceutical equipment M k The fuzzy completion time of the most recent pharmaceutical process and the pharmaceutical process O ij The larger of the fuzzy completion times of the preceding pharmaceutical process (i.e., the (j-1)th process of batch i drug) is taken as the completion time of the pharmaceutical process O. ij Fuzzy start time

[0102] S5: According to pharmaceutical process O ij In pharmaceutical equipment M k Fuzzy execution time Calculate the fuzzy end time of this process.

[0103] S6: Increment the process number of the drug with batch number i that is about to be performed by 1, and determine whether c is equal to the total number of processes n for all batches: if yes, complete the scheduling plan; otherwise, let c = c + 1 and return to S2.

[0104] In S107, the optimized scheduling scheme is obtained by solving the pharmaceutical scheduling model and the scheduling coding model.

[0105] According to the example embodiment, the improved multi-objective quantum particle swarm optimization algorithm can be used to optimize the pharmaceutical scheduling model and the scheduling encoding and decoding model to obtain an optimized scheduling scheme.

[0106] According to one embodiment, an improved multi-objective quantum particle swarm optimization algorithm is used to solve the model, and the solution process is as follows: Figure 3The flowchart shown is illustrated. This algorithm is designed based on the quantum particle swarm optimization (PSO) algorithm, improving its iterative behavior and implementing a mapping rule from continuous particle positions to discrete codes for the aforementioned scheduling encoding / decoding model. Furthermore, it incorporates Pareto theory to collect non-dominated solutions, enabling the algorithm to provide diverse and high-quality scheduling schemes in solving multi-objective problem models. Here, each particle corresponds to a possible scheduling scheme, namely the aforementioned pharmaceutical batch process priority and the pharmaceutical equipment corresponding to each pharmaceutical process.

[0107] S1: Initialize the basic parameters of the algorithm, including particle upper and lower limits, maximum number of iterations, and external archive capacity.

[0108] The external archive is used to store non-dominated solutions for all solutions. Because new solutions are constantly emerging during algorithm execution, the external archive must be continuously updated. The capacity of the external archive refers to the maximum number of solutions it can store.

[0109] S2: Randomly generate an initial continuous population. The dimension of each individual in the population is equal to the total length of the scheduling code, which is twice the total number of pharmaceutical batch processes, 2n. The first n positions represent the pharmaceutical batch process part, and the last n positions represent the pharmaceutical equipment part.

[0110] S3: Based on the characteristics of the scheduling encoding / decoding model, continuous particles are mapped to scheduling codes. The mapping is performed in two parts:

[0111] For the pharmaceutical manufacturing process, the initial pharmaceutical manufacturing process code is first defined and arranged in ascending order according to the pharmaceutical batch number and the number of pharmaceutical manufacturing processes for each production batch.

[0112] According to one embodiment, [1, 1, 1, 2, 2, 3, 3] corresponds to three batches of production tasks. Pharmaceutical batch 1 has three pharmaceutical processes, while pharmaceutical batches 2 and 3 each have two pharmaceutical processes. Then, the portions representing the pharmaceutical processes in the continuous particles are arranged in descending order to obtain the sorted indices. Finally, the initial pharmaceutical process codes are rearranged according to the sorted indices to complete the mapping. (See reference...) Figure 4 As shown in the diagram, the values ​​of the particle pharmaceutical process in this case are [-3.7, 2.1, -6.1, -7.9, 3.0, 5.5, 1.9]. After sorting in descending order, the index relative to the original position is [6, 5, 2, 7, 1, 3, 4]. Then, after arranging the initial pharmaceutical process code [1, 1, 1, 2, 2, 3, 3] according to this index, the pharmaceutical process code [3, 2, 1, 3, 1, 1, 2] can be obtained.

[0113] For the pharmaceutical equipment section, the following mapping formula is used:

[0114]

[0115] Where, x i Let z be the value of the particle in a certain dimension i of the pharmaceutical equipment section, with upper and lower limits of [-ε, ε], z i Represents x i The number of optional pharmaceutical equipment for the corresponding process, m i This is the index of the selected device among the available pharmaceutical devices.

[0116] S4: Decode the scheduling scheme and calculate the objective function values. Take the non-dominated solution as the initial external archive, and at the same time generate the individual optimal position solution and the global optimal position solution.

[0117] S5: Improve and calculate the average optimal position and local attractors of the population based on the weighting factor and the variable Gaussian distribution random numbers, and update the population, specifically:

[0118] The improved average optimal position update formula:

[0119]

[0120] Where mbest is the improved average optimal position, f() represents the compromise fitness of the solution within the parentheses, and max(f) j ), min(f j Let p be the maximum and minimum values ​​of all obtained solutions on the objective function j, k be the total number of solutions to the objective (minimizing the maximum completion time and pharmaceutical cost), and p be the maximum and minimum values ​​of all solutions to the objective function j. i or p ii Each represents the optimal position for an individual.

[0121] Improved local attractor update formula:

[0122]

[0123] Among them, S ij For particle x i The corresponding improved local attractor, N(μ) t ,1.5) are random numbers with a variable Gaussian distribution whose mean increases linearly with the number of iterations, p ij and g j Represents x i The values ​​of the individual optimal position and the global optimal position of the population in dimension j.

[0124] Furthermore, the population renewal formula is:

[0125]

[0126] Where β is the shrinking and expanding system, which decreases linearly with the number of iterations, and r is a random number in the range [0, 1].

[0127] S6: Remap the updated particles to scheduling codes, decode them, and calculate the objective function values ​​to obtain the compromise fitness. Compare this compromise fitness with the compromise fitness of the corresponding individual optimal position. If the new particle has a better compromise fitness, update the corresponding individual optimal position to the new particle and record the changed individual optimal position. The formula for calculating the compromise fitness is the same as f(p) used in S4 to calculate the average optimal position. i The calculation formula is the same.

[0128] S7: Merge the optimal positions of the new population and individuals whose positions have changed, obtain their non-dominated solution sets, and compare them one by one with the solutions in the external archive. Remove old particles with dominated records from the external archive, and add new particles without dominated records to the archive. The specific details regarding the non-dominated solution sets and domination relationships are as follows:

[0129]

[0130] Among them, PS * Represents the non-dominated solution set; x * Represents any non-dominated solution; x represents the absence of a solution; x represents any feasible solution within the specified range; X f A represents the set of feasible solutions within the specified range; A < B means that A dominates B, that is, for any optimization objective, A is no worse than B, and there exists at least one optimization objective that A is better than B.

[0131] S8: Calculate the crowding entropy of the external archive, eliminate solutions with low crowding that exceed the external archive's capacity one by one, and take the particle with the highest crowding as the globally optimal position. The specific formula for calculating the crowding entropy is as follows:

[0132]

[0133] Among them, CE i The entropy represents the crowding degree of the i-th solution in the external archive within the current archive; max(f j ) and min(f j ) represent the maximum and minimum values ​​of the current solution result for the j-th objective, respectively; du ij and dl ij This represents the absolute value of the difference between the i-th solution and the previous and next solutions at target j after sorting the solutions in the archive according to target j.

[0134] S9: Determine if the maximum number of iterations has been reached. If so, output the current external archive and map it to a specific scheduling scheme to complete the solution of the scheduling scheme; otherwise, return to S4.

[0135] This embodiment also provides an experimental verification method to verify the performance of the designed scheduling optimization method. The main steps of this method include:

[0136] The effectiveness of the proposed improved multi-objective quantum particle swarm optimization (IMOQPSO) algorithm was verified using simulation software and test data from a certain scheduling cycle in a pharmaceutical solid dosage form workshop, and simulation results were obtained.

[0137] The alternative solutions obtained by IMOQPSO are compared with other similar algorithms using the C-measure, thereby verifying the superiority of IMOQPSO in solving the multi-dimensional objective pharmaceutical solid dosage form workshop scheduling problem.

[0138] The C-measure, or Cover Set Measure, is used to compare the degree of dominance between two sets of multi-objective schemes. The specific formula is as follows:

[0139]

[0140] Where a and b represent a solution in the non-dominated solution set output by algorithms A and B, respectively, and |·| represents the number of elements in the set. If C(A, B) > C(B, A), then the result of algorithm A is considered to be better than that of algorithm B.

[0141] Parameter settings: The algorithms used in the experiment included an improved multi-objective quantum particle swarm optimization (QPSO) algorithm, a multi-objective genetic algorithm based on fast non-dominated sorting, a QPSO algorithm with external archive collection of non-dominated solutions, an artificial bee colony algorithm, and a particle swarm optimization (PSO) algorithm. The maximum number of evolutions was 400, the population size was 30, the contraction-expansion coefficients of the improved multi-objective QPSO algorithm and the quantum particle swarm optimization algorithm decreased linearly from 1 to 0.5, the crossover probability of the genetic algorithm was 0.8, the mutation probability was 0.2, the particle confidence levels of the PSO algorithm were c1 = 0.1, c2 = 0.9, and the inertia coefficient w decreased linearly from 1 to 0. In the artificial bee colony algorithm, the number of hired bees and scout bees was the same as the population size, and the maximum number of attempts for a single nectar source was trail = 4.

[0142] Figure 5 The Pareto front comparison diagram shows the simulation experiment of the pharmaceutical process scheduling optimization method of the solid dosage form workshop according to the embodiment of this application.

[0143] Figure 5 Comparison of Pareto fronts mapped by taking the non-dominated solution set of the union of the results of 10 runs for each algorithm shows that the front of IMOQPSO is superior in both convergence and diversity. Decision-makers can choose the appropriate scheduling scheme from it according to actual needs.

[0144] Figure 6 This diagram illustrates the results obtained by the IMOQPSO algorithm for optimizing the pharmaceutical process scheduling scheme of a solid dosage form workshop according to an embodiment of this application.

[0145] Figure 6This is a fuzzy Gantt chart corresponding to a randomly selected scheme. During actual production, the scheduler can perform relevant scheduling operations based on this chart.

[0146] Figure 7 A block diagram of a pharmaceutical process scheduling optimization device for a solid dosage form workshop according to an embodiment of this application is shown.

[0147] like Figure 7 As shown, the pharmaceutical process scheduling optimization device for the solid dosage form workshop includes a parameter extraction module 701, a scheduling modeling module 703, a coding modeling module 705, and a solution optimization module 709. Wherein:

[0148] The parameter extraction module 701 obtains production parameter information based on historical pharmaceutical information;

[0149] The scheduling modeling module 703 establishes a pharmaceutical scheduling model based on production parameter information and pharmaceutical process information. The pharmaceutical scheduling model is used to optimize the maximum completion time and pharmaceutical cost. The pharmaceutical process information includes pharmaceutical batch process information and pharmaceutical equipment information.

[0150] Encoding modeling module 705 establishes a scheduling encoding and decoding model between pharmaceutical batch process information and pharmaceutical equipment information;

[0151] The optimization module 709 solves the pharmaceutical scheduling model and the scheduling encoding and decoding model to obtain an optimized scheduling scheme, which is the relationship between pharmaceutical process information and pharmaceutical equipment information.

[0152] This device performs functions similar to those described above; other functions can be found in the previous descriptions and will not be repeated here.

[0153] According to some embodiments, see Table 1 for experimental information: the experimental data comes from a well-known domestic pharmaceutical company. Table 1 shows the basic information on the production time required for each batch of drugs and pharmaceutical equipment. The pharmaceutical processes involved include granulation and mixing, filling, tableting, coating, and packaging. The process flow is arranged from left to right. Blank parts represent processes that do not include that batch of drugs. Table 2 shows the unit time operating cost of each pharmaceutical equipment. Among them, J i It is the pharmaceutical batch number, M k It is the serial number of the pharmaceutical equipment. It is J i Batch of drugs in pharmaceutical equipment M k The fuzzy completion time required for production. For J i The cost of pharmaceutical raw materials for a batch of drugs, For pharmaceutical equipment M k The unit time operating cost.

[0154] Table 1. Basic Information on Production Time Required for Each Batch of Drugs and Pharmaceutical Equipment

[0155]

[0156]

[0157] Table 2. Unit Time Operating Costs of Various Pharmaceutical Equipment

[0158]

[0159] Table 3 presents a statistical comparison of the C-measure results for each algorithm. In Table 3, IMOQPSO is the improved multi-objective quantum particle swarm optimization algorithm, QPSO is the quantum particle swarm optimization algorithm, NSGA-II is the multi-objective genetic algorithm, and ABC and PSO are the artificial bee colony algorithm and particle swarm optimization algorithm, respectively.

[0160] Table 3. Comparison Results of Simulation Experiments

[0161]

[0162]

[0163] As can be seen from Table 3, the average C-measure of the proposed IMOQPSO compared to other algorithms is between 0.68 and 1. In the best case, the non-dominated solution of IMOQPSO can even dominate all the solutions of other algorithms, while in the worst case, the dominated ratio of IMOQPSO is only 0.2. This fully demonstrates that the Pareto solution set obtained by IMOQPSO can more rationally schedule the processing sequence of drugs and the allocation of equipment, thereby improving the input-output ratio of the workshop.

[0164] Figure 8 A block diagram of an electronic device according to an exemplary embodiment is shown.

[0165] The following reference Figure 8 To describe an electronic device 800 according to this embodiment of the present application. Figure 8 The electronic device 800 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0166] like Figure 8 As shown, the electronic device 800 is presented in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, a bus 830 connecting different system components (including storage unit 820 and processing unit 810), a display unit 840, etc.

[0167] The storage unit stores program code, which can be executed by the processing unit 810 to perform the methods described in this specification according to various exemplary embodiments of this application. For example, the processing unit 810 can perform the methods described above.

[0168] Storage unit 820 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 8201 and / or cache memory 8202, and may further include a read-only memory (ROM) 8203.

[0169] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0170] Bus 830 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0171] Electronic device 800 can also communicate with one or more external devices 8001 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 800, and / or with any device that enables electronic device 800 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 850. Furthermore, electronic device 800 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 860. Network adapter 860 can communicate with other modules of electronic device 800 via bus 830. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0172] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. The technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, or network device, etc.) to execute the methods described above according to the embodiments of this application.

[0173] Software products may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example,, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0174] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0175] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0176] The aforementioned computer-readable medium carries one or more programs, which, when executed by a device, cause the computer-readable medium to perform the aforementioned functions.

[0177] Those skilled in the art will understand that the above modules can be distributed in the device as described in the embodiments, or they can be modified accordingly and placed in one or more devices that are unique to this embodiment. The modules in the above embodiments can be combined into one module, or they can be further divided into multiple sub-modules.

[0178] Through the description of the above embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this application.

[0179] In another aspect, this application also provides a computer-readable medium, which may be included in the apparatus described in the above embodiments; or it may exist independently and not assembled into the apparatus. The computer-readable medium carries one or more programs, which, when executed by the apparatus, cause the apparatus to: obtain production parameter information based on historical pharmaceutical information; establish a pharmaceutical scheduling model based on the production parameter information and pharmaceutical process information, the pharmaceutical scheduling model being used to optimize the maximum completion time and pharmaceutical cost, the pharmaceutical process information including pharmaceutical batch process information and pharmaceutical equipment information; establish a scheduling encoding and decoding model between the pharmaceutical batch process information and the pharmaceutical equipment information; and solve the pharmaceutical scheduling model and the scheduling encoding and decoding model to obtain an optimized scheduling scheme, the scheduling scheme being the association between the pharmaceutical process information and the pharmaceutical equipment information.

[0180] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0181] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this application. Furthermore, any changes or modifications made by those skilled in the art based on the ideas of this application, and on the specific implementation methods and application scope of this application, are all within the scope of protection of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for optimizing pharmaceutical process scheduling in a solid dosage form workshop, comprising: Production parameter information is obtained based on historical pharmaceutical information, including: data cleaning and processing of the historical pharmaceutical information to obtain the minimum, most likely, and maximum values ​​of single-process processing time, equipment operating cost, and pharmaceutical raw material cost; A pharmaceutical scheduling model is established based on the production parameter information and pharmaceutical process information. The pharmaceutical scheduling model is used to optimize the maximum completion time and pharmaceutical cost. The pharmaceutical process information includes pharmaceutical batch process information and pharmaceutical equipment information. Establish a scheduling encoding and decoding model between the pharmaceutical batch process information and the pharmaceutical equipment information; An optimized scheduling scheme is obtained by solving the pharmaceutical scheduling model and the scheduling encoding / decoding model. This scheduling scheme represents the association between the pharmaceutical process information and the pharmaceutical equipment information. The establishment of a pharmaceutical scheduling model based on the production parameter information and pharmaceutical process information includes: Based on the minimum, most likely, and maximum values ​​of the single-process processing time, the equipment operating cost, and the pharmaceutical raw material cost, triangular fuzzy numbers are established for the single-process processing time, pharmaceutical raw material cost, and equipment operating cost, respectively. Establish pharmaceutical constraint relationships based on the pharmaceutical batch process information and the pharmaceutical equipment information; Based on the triangular fuzzy numbers representing the single-process processing time, the cost of pharmaceutical raw materials, and the equipment operating cost, objective functions for the maximum completion time and the cost of fuzzy pharmaceutical manufacturing are established; where... The establishment of pharmaceutical constraint relationships based on the pharmaceutical batch process information and the pharmaceutical equipment information includes: ， ， ， ， ， in, n The total number of batches of pharmaceuticals. m This represents the total number of pharmaceutical equipment. u i For the first i The total number of pharmaceutical manufacturing processes included in a batch of drugs. For the first i The first batch of drugs j Is the process selected at number ? k Produced on pharmaceutical equipment, For the first i The first batch of drugs j The process is in t Is the time numbered k Produced on pharmaceutical equipment, and The first i The first batch of drugs j Step-by-step process and its preceding steps i The first batch of drugs j-1 The process is numbered as follows k The fuzzy completion time on pharmaceutical equipment Infinite For the first p The first batch of drugs q The vague start time of each process step z ijpqk For the first p The first batch of drugs q Step and the first i The first batch of drugs j Are all processes numbered as follows? k Pharmaceutical equipment production, For the first i The first batch of drugs j The process is numbered as follows k The fuzzy start time on pharmaceutical equipment For the first i The first batch of drugs j The process is numbered as follows k The ambiguous production time on pharmaceutical equipment; among which, The objective function for establishing the maximum completion time and fuzzy pharmaceutical cost based on the triangular fuzzy number of the single-process processing time, the cost of pharmaceutical raw materials, and the equipment operating cost includes: Based on the triangular fuzzy number of the single-process processing time, an objective function for the maximum completion time of fuzzy pharmaceutical manufacturing is established: ， in, This refers to the maximum completion time for the fuzzy pharmaceutical manufacturing process. Representing the i Vague completion time for batches of drugs For the first i The first batch of drugs i The process is numbered as follows k Fuzzy completion times on pharmaceutical equipment; A fuzzy pharmaceutical cost objective function is established based on the triangular fuzzy numbers of the pharmaceutical raw material costs and the equipment operating costs: ， in, For the aforementioned fuzzy pharmaceutical cost, For the first i The vague pharmaceutical raw material cost of a batch of drugs; For the number k The fuzzy equipment operating cost of pharmaceutical equipment; The step of solving the pharmaceutical scheduling model and the scheduling encoding / decoding model to obtain an optimized scheduling scheme includes: using an improved multi-objective quantum particle swarm optimization algorithm to optimize and solve the pharmaceutical scheduling model and the scheduling encoding / decoding model to obtain an optimized scheduling scheme.

2. The method as described in claim 1, characterized in that, The establishment of a scheduling encoding / decoding model between the pharmaceutical batch process information and the pharmaceutical equipment information includes: The correspondence between the pharmaceutical batch process information and the pharmaceutical equipment information is constructed based on the pharmaceutical process priority coding and pharmaceutical equipment coding.

3. A pharmaceutical process scheduling optimization device for a solid dosage form workshop performing the method of claim 1 or 2, comprising: The parameter extraction module obtains production parameter information based on historical pharmaceutical information; The scheduling modeling module establishes a pharmaceutical scheduling model based on the production parameter information and pharmaceutical process information. The pharmaceutical scheduling model is used to optimize the maximum completion time and pharmaceutical cost. The pharmaceutical process information includes pharmaceutical batch process information and pharmaceutical equipment information. The coding modeling module establishes a scheduling encoding and decoding model between the pharmaceutical batch process information and the pharmaceutical equipment information. The optimization module solves the pharmaceutical scheduling model and the scheduling encoding / decoding model to obtain an optimized scheduling scheme, which is the association between the pharmaceutical process information and the pharmaceutical equipment information.

4. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in claim 1 or 2.

5. A non-transitory computer-readable storage medium having stored thereon computer-readable instructions that, when executed by a processor, cause the processor to perform the method as described in claim 1 or 2.

Images