A pipeline experiment automatic scheduling method, system and related device
By employing random generation of permutation arrays, crossover operations, and mutation operations on the automated detection line, combined with the linkage gene probability in biological genetics, the target population is determined, thus solving the problem of inconsistent detection time and achieving optimal efficiency in the detection experiment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHENGDU LANTHANUM & BARIUM TECH CO LTD
- Filing Date
- 2025-12-30
- Publication Date
- 2026-05-29
AI Technical Summary
The testing times at different stations on the existing automated production line are inconsistent, and improper testing sequences result in low efficiency of the production line testing experiments, failing to achieve optimal efficiency.
By randomly generating a permutation array as the initial population, performing crossover and mutation operations, introducing the probability of linked genes from biological genetics, determining the target population, and selecting the optimal detection order for detection.
The efficiency of the testing experiment has been optimized, enabling the testing experiment to achieve its optimal efficiency.
Smart Images
Figure CN122114429A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of testing and experimental technology, and in particular to an automatic scheduling method, system and related equipment for automated production line experiments. Background Technology
[0002] On the laboratory's automated testing line, robotic arms replace human hands, tracks and transmission systems replace human legs, and AI assists the human brain, enabling the entire testing experiment to become intelligent and automated, providing users with more automatic, intelligent, convenient, and cost-effective laboratory automation solutions.
[0003] However, the inconsistent testing times and improper testing sequences at each station on the existing automated production line can lead to low efficiency in testing experiments, preventing the production line from achieving optimal efficiency. Summary of the Invention
[0004] To overcome the problem that inconsistent testing times and improper testing sequences at various workstations on existing automated production lines lead to low efficiency in testing experiments and prevent the achievement of optimal efficiency, this invention provides an automatic scheduling method, system, and related equipment for production line experiments.
[0005] Firstly, in order to solve the above-mentioned technical problems, the present invention provides an automatic scheduling method for pipeline experiments, comprising: A random permutation array is generated as the initial population, where the permutation array represents the different detection orders of each detection experiment, and each detection order is an individual in the initial population; The initial population is used as the parent generation, and a crossover operation is performed to determine the first offspring. Individuals in the initial population are paired up to determine the paired individuals, and the paired individuals are used as the parents to perform mutation operations to determine the second offspring; in this process, the probability of linked genes in biological genetics is introduced to perform mutation operations on the parents. The target population is determined based on the first offspring, the second offspring, and the parent generation; The detection is performed according to the detection order corresponding to each individual in the target population, and the total first detection time corresponding to each individual is determined. Individuals that meet the first preset requirements within each first detection total duration are taken as target individuals, and each detection experiment is performed according to the detection order corresponding to the target individuals.
[0006] Secondly, the present invention provides an automatic scheduling system for production line experiments, comprising: The initial population generation module is used to randomly generate a permutation array as the initial population. The permutation array represents the different detection orders of each detection experiment, and each detection order is an individual in the initial population. The first offspring determination module is used to determine the first offspring by performing a crossover operation on the initial population as the parent generation. The second offspring determination module is used to pair individuals in the initial population, determine the paired individuals, and use the paired individuals as the parents to perform mutation operations to determine the second offspring; in this process, the probability of linked genes in biological genetics is introduced to perform mutation operations on the parents. The target population determination module is used to determine the target population based on the first offspring, the second offspring, and the parent generation. The first detection total duration determination module is used to determine the first detection total duration for each individual in the target population according to the detection order corresponding to each individual. The detection module is used to select individuals that meet the first preset requirements in each first total detection time as target individuals, and to perform detection on each detection experiment according to the detection order corresponding to the target individuals.
[0007] Thirdly, the present invention provides a computing device, including a memory, a processor, and a program stored in the memory and running on the processor, wherein the processor executes the program to implement the steps of the above-described automatic scheduling method for pipeline experiments.
[0008] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a terminal device, cause the terminal device to perform the steps of the above-described automatic scheduling method for pipeline experiments.
[0009] The beneficial effects of this invention are as follows: By randomly permuting the detection order of each detection experiment to generate a permutation array, and performing crossover and mutation operations respectively, wherein the mutation operation introduces the probability of linked genes in biology, and finally combining the first offspring, second offspring, and parent generation, the target population is determined, and the optimal detection order (target individual) in the target population is selected for detection, thus achieving optimal detection efficiency. This application uses a genetic algorithm to schedule and arrange tasks, ensuring that genes with excellent fitness are inherited by the next generation, thereby optimizing detection efficiency. Attached Figure Description
[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0011] Figure 1 This is a flowchart illustrating an automatic scheduling method for pipeline experiments according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the experimental detection results of an embodiment of the present invention; Figure 3This is a schematic diagram of the structure of an automated scheduling system for production line experiments according to an embodiment of the present invention. Detailed Implementation
[0012] The following embodiments are further explanations and supplements to the present invention and do not constitute any limitation on the present invention.
[0013] The following describes an automatic scheduling method, system, and related equipment for pipeline experiments according to an embodiment of the present invention, with reference to the accompanying drawings.
[0014] like Figure 1 As shown, this embodiment of the invention provides an automatic scheduling method for pipeline experiments, including: S1. Randomly generate a permutation array as the initial population, where the permutation array represents the different detection orders of each detection experiment, and each detection order is an individual in the initial population.
[0015] S2. Using the initial population as the parent generation, perform a crossover operation to determine the first offspring.
[0016] S3. Pair individuals in the initial population to determine the paired individuals, and use the paired individuals as the parents to perform mutation operations to determine the second offspring; wherein, the probability of linked genes in biological genetics is introduced to perform mutation operations on the parents.
[0017] S4. Determine the target population based on the first offspring, the second offspring, and the parent generation.
[0018] S5. Perform the detection according to the detection order corresponding to each individual in the target population, and determine the total first detection time for each individual.
[0019] S6. Select the individuals that meet the first preset requirements in each first detection total duration as target individuals, and perform detection experiments according to the detection order corresponding to the target individuals.
[0020] In this embodiment, the detection order of each detection experiment is randomly permuted to generate a permutation array. Crossover and mutation operations are then performed on each array. The mutation operation incorporates the probability of linked genes from biology. Finally, the first, second, and parent generations are combined to determine the target population, and the optimal detection order (target individual) within the target population is selected for detection, thus maximizing the efficiency of the detection experiments. This application uses a genetic algorithm to schedule and arrange tasks, ensuring that genes with excellent fitness are inherited by the next generation, thereby optimizing detection efficiency.
[0021] The detection experiment in this embodiment is applicable to all detection items, such as hepatitis B detection, pneumonia detection, and virus detection.
[0022] In this embodiment, randomly generating a full permutation array means randomly arranging the detection order of each detection experiment. For example, given detection experiments 0, 1, 2, 3, 4, and 5 (hereinafter referred to as numbers 0-5), each detection experiment needs to be performed sequentially at different workstations. The resulting full permutation array is as follows: [2,3,0,1,4,5]、[2,3,0,1,4,5]、[2,3,0,1,4,5]、[2,3,0,1,4,5]、[2,3,0,1,4,5]、[2,3,0,1,4,5]、[2,3,0,1,4,5]、[2,3,0,1,4,5].
[0023] Taking individuals [2, 3, 0, 1, 4, 5] as an example, the detection order is: Experiment 2, Experiment 3, Experiment 0, Experiment 1, Experiment 4, Experiment 5.
[0024] In this embodiment, the individual that meets the first preset requirement refers to one or more individuals in the target population with the smallest total detection time.
[0025] In this embodiment, the crossover operation refers to randomly selecting two genes from an individual and exchanging them, resulting in a new offspring. For example, [2, 3, 0, 1, 4, 5] undergoes crossover mutation to obtain [2, 0, 3, 1, 4, 5].
[0026] Optionally, the paired individuals can be used as parents to perform mutation operations to determine the second offspring, including: The preset or adjacent positions of paired individuals are used as the linked gene positions; Select one individual from each linked gene location as the second offspring.
[0027] In this embodiment, linked genes refer to genes located on the same chromosome that tend to be inherited together by offspring. By incorporating the probability of linked genes into the genetic algorithm in this embodiment, it is ensured that genes with excellent fitness are inherited by the next generation.
[0028] In this embodiment, the linked gene can be a gene at a preset position (relative position), a gene at an adjacent position, or a gene with other special requirements. For example, any two individuals in the initial population are paired to obtain paired individuals, namely P1 and P2. The corresponding linked genes can be found from the two parents recursively, i.e., {{P2(x1)...,P1(y1)...},{P2(x2)...,P1(y2)...},...{P2(x...}, ... n ..., P1(y n )...}},x n and y nThat is, the gene at the relative position (the nth position).
[0029] Through hybridization, offspring can randomly select the corresponding linked gene {P2(x)}. n ..., P1(y n One of the following is selected from the list of x, ..., and the probability is 50%; that is, P2(x) n ), or P1(y n This ensures that the offspring's genes all come from the parents, while also allowing for different combinations of genes in the offspring.
[0030] To illustrate with another example, see below: p1= [1, 5, 3, 4, 8, 7, 6, 2, 9]; p2= [5, 1, 4, 3, 7, 6, 8, 9, 2]; P1 and P2 are the parent generation; The corresponding linked genes are positions 1-2, 3-4, 5-7, and 8-9: {{1, 5}, {5, 1}}, {{3, 4}, {4, 3}}, {{8, 7, 6}, {7, 6, 8}}, {{2, 9}, {9, 2}}.
[0031] The corresponding offspring individuals are: C = [{{1, 5}, {5, 1}} * 0.5 probability, {{3, 4}, {4, 3}} * 0.5 probability, {{8, 7, 6}, {7, 6, 8}} * 0.5 probability, {{2, 9}, {9, 2}} * 0.5 probability].
[0032] The target genes in the final offspring are {1, 5}, {4, 3}, {8, 7, 6} and {2, 9}, respectively, that is, the offspring can be: [1, 5, 4, 3, 8, 7, 6, 2, 9].
[0033] Optionally, the first, second, and parent generations can be used as a new population. By updating fitness and removing individuals with poor fitness, the target population can be determined, including: The first offspring, the second offspring, and the parent generation are considered as a new population. Calculate the total second detection time for each individual in the new population; If the total second detection time for each individual in the new population meets the second preset requirement, then the new population will be used as the target population.
[0034] In this embodiment, the method for determining the second total detection time is the same as the method for determining the first total detection time. The method for determining the first total detection time will be described below, so it will not be repeated here.
[0035] In this embodiment, the second preset requirement can be met if the total detection time for each individual is less than the preset threshold, or if the total detection time for n% or more of the total number of individuals (n is a positive integer from 0 to 100) is less than the preset threshold, or if the total detection time for any individual is less than the preset threshold. The setting can be adjusted according to the actual situation.
[0036] Optionally, if the total detection time for each individual in the new population meets the second preset requirement, then the new population is used as the target population, further including: If the total second detection time of each individual in the new population does not meet the second preset requirement, then the new population is used as the new initial population, crossover and mutation operations are performed, and the fitness is updated to determine the new target population until the total second detection time of each individual in the new target population meets the second preset requirement.
[0037] In this embodiment, the fitness is updated through multiple iterations until the total detection time of each individual in the new population meets the second preset requirement, thereby obtaining the optimal solution arrangement order and improving the efficiency of the detection experiment.
[0038] In this embodiment, fitness refers to the total detection time for each individual in the population.
[0039] Optionally, detection is performed according to the detection order corresponding to each individual in the target population, and the total first detection time for each individual is determined, including: Assign preset parallel resources to a single workstation; where preset parallel resources are the amount of resources consumed by a single workstation in performing a testing experiment; Each test experiment is assigned a preset consumption amount; where the preset consumption amount is the consumption value of preset parallel resources when the test experiment is placed in a single workstation. According to the detection order corresponding to each individual in the target population, each detection experiment is placed in the corresponding workstation and detected according to the preset constraints, and the detection time of each detection experiment in each workstation is determined. Based on the detection time, calculate the first total detection time for each individual.
[0040] In this embodiment, the testing experiment is carried out in a production line at a workstation. A workstation refers to the testing equipment corresponding to the testing item, such as a pipetting workstation or a sealing machine. Production line testing means that multiple workstations are connected in sequence. The testing experiment will start from the first workstation. After the test is completed, the robotic arm will move to the second workstation for testing, and so on, until the last workstation is completed, thus completing the testing experiment.
[0041] Furthermore, since a single workstation can perform multiple testing experiments simultaneously, a preset parallel resource can be assigned to each workstation. The preset parallel resource refers to the amount of resources consumed by a single workstation in performing a testing experiment. A preset consumption amount is then assigned to each testing experiment, which refers to the consumption value of the preset parallel resource consumed by a single workstation in a testing experiment. For example, if the preset consumption amount for testing experiment 1 is 1, the preset consumption amount for testing experiment 2 is 1, the preset consumption amount for testing experiment 3 is 3, and the preset parallel resource for a single workstation A is 4, then workstation A can simultaneously perform testing experiments 1 and 2, or testing experiments 1 and 3, or testing experiments 2 and 3.
[0042] For example, suppose there are 6 testing experiments and 5 workstations, where: The detection order is [2, 5, 4, 3, 0, 1].
[0043] The testing times for each test at each workstation are as follows: Test 0 = [8, 14, 35, 9, 80], Test 1 = [8, 22, 35, 9, 60], Test 2 = [4, 7, 22, 7, 120], Test 3 = [8, 22, 22, 9, 75], Test 4 = [12, 33, 22, 11, 120], Test 5 = [4, 11, 35, 7, 120]. Taking Test 0 = [8, 14, 35, 9, 80] as an example, this means that the testing times for Test 0 at the five workstations are 8 minutes, 14 minutes, 35 minutes, 9 minutes, and 80 minutes, respectively.
[0044] The preset resource consumption for each testing experiment at each workstation is as follows: Testing Experiment 0 = [1, 1, 2, 1, 1], Testing Experiment 1 = [1, 1, 2, 1, 1], Testing Experiment 2 = [1, 1, 1, 1, 1], Testing Experiment 3 = [1, 1, 2, 1, 1], Testing Experiment 4 = [1, 1, 3, 1, 1], Testing Experiment 5 = [1, 1, 1, 1, 1]. Taking Testing Experiment 0 = [1, 1, 2, 1, 1] as an example, this means that the preset parallel resources consumed by Testing Experiment 0 at the five workstations are 1, 1, 2, 1, and 1 respectively. In this embodiment, the preset parallel resources for each workstation need to be set in advance, for example, [1, 1, 4, 1, 4], indicating that the preset parallel resources for workstations 1-5 are 1, 1, 4, 1, and 4 respectively.
[0045] Based on the above, the total detection time corresponding to the detection sequence [2, 5, 4, 3, 0, 1] is 217 minutes.
[0046] Optional, preset constraints include: Each testing experiment proceeds sequentially from the first workstation to the last workstation; Each test can only begin when the current workstation is idle; Each workstation calculates the remaining preset parallel resources based on the preset consumption amount corresponding to each test experiment. If the workstation has remaining preset parallel resources, multiple test experiments can be performed in parallel. When the preset consumption amount for each test experiment is less than the remaining preset parallel resources of the current workstation, the test can proceed smoothly until the current test is completed. The total number of tests running in parallel at each workstation must not exceed the preset parallel resources.
[0047] A specific example will be used to illustrate this, as follows: A total of 6 testing labs (0-5) and 5 workstations were set up, including: Randomly generate a permutation array as the initial population to obtain {[2,3,0,1,4,5],[2,3,0,1,4,5],[2,3,0,1,4,5],[2,3,0,1,4,5],[2,3,0,1,4,5],[2,3,0,1,4,5],[2,3,0,1,4,5],[2,3,0,1,4,5]}.
[0048] The testing times for each test at each workstation are as follows: Test 0 = [8, 14, 35, 9, 80], Test 1 = [8, 22, 35, 9, 60], Test 2 = [4, 7, 22, 7, 120], Test 3 = [8, 22, 22, 9, 75], Test 4 = [12, 33, 22, 11, 120], Test 5 = [4, 11, 35, 7, 120].
[0049] The preset consumption amounts for each test experiment at each workstation are as follows: Test Experiment 0 = [1, 1, 2, 1, 1], Test Experiment 1 = [1, 1, 2, 1, 1], Test Experiment 2 = [1, 1, 1, 1, 1], Test Experiment 3 = [1, 1, 2, 1, 1], Test Experiment 4 = [1, 1, 3, 1, 1], Test Experiment 5 = [1, 1, 1, 1, 1].
[0050] The preset parallel resources corresponding to workstations 1-5 are [1, 1, 4, 1, 4].
[0051] Using the genetic algorithm in this embodiment, crossover, mutation, and cyclic operations are performed on the initial population to obtain the target population as {[2, 5, 4, 3, 0, 1], [2, 5, 4, 0, 3, 1], [5, 2, 4, 3, 0, 1], [5, 2, 4, 0, 3, 1], [5, 4, 2, 0, 3, 1], [5, 4, 2, 3, 0, 1], [2, 5, 4, 1, 0, 3], [2, 5, 4, 0, 1, 3], [5, 2, 4, 0, 1, 3], [5, 2, 4, 1, 0, 3]}.
[0052] The total detection time is: [2, 5, 4, 3, 0, 1], total detection time = 217 minutes; [2, 5, 4, 0, 3, 1], total detection time = 217 minutes; [5, 2, 4, 3, 0, 1], total detection time = 217 minutes; [5, 2, 4, 0, 3, 1], total detection time = 217 minutes; [5, 4, 2, 0, 3, 1], total detection time = 218 minutes; [5, 4, 2, 3, 0, 1], total detection time = 218 minutes; [2, 5, 4, 1, 0, 3], total detection time = 219 minutes; [2, 5, 4, 0, 1, 3], total detection time = 219 minutes; [5, 2, 4, 0, 1, 3], total detection time = 219 minutes; [5, 2, 4, 1, 0, 3], Total detection time = 219 minutes.
[0053] That is, [2, 5, 4, 3, 0, 1], [2, 5, 4, 0, 3, 1], [5, 2, 4, 3, 0, 1], and [5, 2, 4, 0, 3, 1] can be used as target individuals, and the five detection experiments can be performed according to any corresponding detection order.
[0054] like Figure 2 The image shows the testing experiments performed in the order corresponding to the target individual. These include Influenza (influenza virus detection), HBV (hepatitis B virus detection), Fungal Triple Test (fungal detection), PIV (parainfluenza virus detection), COVID (pneumonia virus detection), and TB DNA (mycobacterium tuberculosis detection). Figure 2As can be seen, Influenza detected the virus first. Its detection time at each station (the vertical axis S1-S5 represent 5 stations) can be referenced to the horizontal axis. It detected influenza A&B-4 at station 1, influenza A&B-7 at station 2, influenza A&B-22 at station 3, influenza A&B-7 at station 4, and influenza A&B-120 at station 5. Simultaneously, Influenza detection occurred in parallel with HBV and the Fungal Triple Test at station 3, in parallel with the Fungal Triple Test at station 4, and in parallel with HBV, the Fungal Triple Test, PIV, and COVID at station 5 (parallel detection is indicated by overlapping areas on the horizontal axis), and so on. The detection mechanisms for HBV, the Fungal Triple Test, PIV, COVID, and TB DNA are the same as Influenza, so they will not be elaborated upon.
[0055] like Figure 3 As shown, this embodiment of the invention provides an automatic scheduling system for pipeline experiments, including: The initial population generation module is used to randomly generate a permutation array as the initial population. The permutation array represents the different detection orders of each detection experiment, and each detection order is an individual in the initial population. The first offspring determination module is used to determine the first offspring by performing a crossover operation on the initial population as the parent generation. The second offspring determination module is used to pair individuals in the initial population, determine the paired individuals, and use the paired individuals as the parents to perform mutation operations to determine the second offspring; in this process, the probability of linked genes in biological genetics is introduced to perform mutation operations on the parents. The target population determination module is used to determine the target population based on the first offspring, the second offspring, and the parent generation. The first detection total duration determination module is used to determine the first detection total duration for each individual in the target population according to the detection order corresponding to each individual. The detection module is used to select individuals that meet the first preset requirements in each first total detection time as target individuals, and to perform detection on each detection experiment according to the detection order corresponding to the target individuals.
[0056] Optionally, the second offspring determination module is specifically used for: The preset or adjacent positions of paired individuals are used as the linked gene positions; Select one individual from each linked gene location as the second offspring.
[0057] Optionally, the target population determination module is specifically used for: The first, second, and parent generations are used as a new population. By updating the fitness and removing individuals with poor fitness, the target population is determined.
[0058] Optionally, the target population determination module is specifically used for: The first offspring, the second offspring, and the parent generation are considered as a new population. Calculate the total second detection time for each individual in the new population; If the total second detection time for each individual in the new population meets the second preset requirement, then the new population will be used as the target population.
[0059] Optionally, the target population determination module further includes: If the total second detection time of each individual in the new population does not meet the second preset requirement, then the new population is used as the new initial population, crossover and mutation operations are performed, and the fitness is updated to determine the new target population until the total second detection time of each individual in the new target population meets the second preset requirement.
[0060] Optionally, the detection module is specifically used for: Assign preset parallel resources to a single workstation; where preset parallel resources are the amount of resources consumed by a single workstation in performing a testing experiment; Each test experiment is assigned a preset consumption amount; where the preset consumption amount is the consumption value of preset parallel resources when the test experiment is placed in a single workstation. According to the detection order corresponding to each individual in the target population, each detection experiment is placed in the corresponding workstation and detected according to the preset constraints, and the detection time of each detection experiment in each workstation is determined. Based on the detection time, calculate the first total detection time for each individual.
[0061] The present invention also provides a computing device, including a memory, a manager, and a program stored in the memory and running on the manager. When the manager executes the program, it implements some or all of the steps of the above-described automatic scheduling method for pipeline experiments.
[0062] The computing device can be a computer, and the corresponding program is computer software. The parameters and steps of the computing device of the present invention can be referred to the parameters and steps in the embodiment of the automatic scheduling method for pipeline experiments in the above text, and will not be repeated here.
[0063] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this disclosure can be embodied in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the invention can also be implemented as a computer program product contained in one or more computer-readable media, which contains computer-readable program code. Computer-readable storage media can be, for example, but not limited to—electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof.
[0064] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0065] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.
Claims
1. An automatic scheduling method for pipeline experiments, characterized in that, include: A random permutation array is generated as the initial population, wherein the permutation array represents the different detection orders of each detection experiment, and each detection order is an individual in the initial population; Using the initial population as the parent generation, a crossover operation is performed to determine the first offspring generation; Individuals in the initial population are paired up to determine the paired individuals, and the paired individuals are used as the parents to perform mutation operations to determine the second offspring; wherein, the probability of linked genes in biological genetics is introduced to perform mutation operations on the parents. The target population is determined based on the first offspring, the second offspring, and the parent generation; The detection is performed according to the detection order corresponding to each individual in the target population, and the first total detection time corresponding to each individual is determined. Individuals that meet the first preset requirements within the total first detection time are taken as target individuals, and each detection experiment is performed according to the detection order corresponding to the target individuals.
2. The method according to claim 1, characterized in that, The step of using paired individuals as parents, performing mutation operations, and determining the second offspring includes: The preset or adjacent positions of paired individuals are used as the linked gene positions; Select one individual from each linked gene location as the second offspring.
3. The method according to claim 1, characterized in that, The determination of the target population based on the first offspring, the second offspring, and the parent generation includes: The first, second, and parent generations are used as a new population. By updating the fitness and removing individuals with poor fitness, the target population is determined.
4. The method according to claim 3, characterized in that, Using the first, second, and parent generations as a new population, the target population is determined by updating fitness, removing individuals with poor fitness, and then eliminating those with low fitness. The first offspring, the second offspring, and the parent generation are considered as a new population. Calculate the total second detection time for each individual in the new population; If the total second detection time for each individual in the new population meets the second preset requirement, then the new population will be used as the target population.
5. The method according to claim 4, characterized in that, If the total detection time for each individual in the new population meets the second preset requirement, then the new population is taken as the target population, and the method further includes: If the total second detection time of each individual in the new population does not meet the second preset requirement, then the new population is used as the new initial population, crossover and mutation operations are performed, and the fitness is updated to determine the new target population until the total second detection time of each individual in the new target population meets the second preset requirement.
6. The method according to claim 1, characterized in that, The step of performing detection according to the detection order corresponding to each individual in the target population, and determining the first total detection time corresponding to each individual, includes: Assign a preset parallel resource to a single workstation; wherein, the preset parallel resource is the amount of resources consumed by a single workstation in performing a detection experiment; Each detection experiment is assigned a preset consumption amount; wherein, the preset consumption amount is the consumption value of preset parallel resources when the detection experiment is placed in a single workstation; According to the detection order corresponding to each individual in the target population, each detection experiment is placed in the corresponding workstation and detected according to the preset constraints, and the detection time of each detection experiment in each workstation is determined. Based on the detection time, calculate the first total detection time for each individual.
7. The method according to claim 6, characterized in that, The preset constraints include: Each testing experiment proceeds sequentially from the first workstation to the last workstation; Each test can only begin when the current workstation is idle; Each workstation calculates the remaining preset parallel resources based on the preset consumption amount corresponding to each test experiment. If the workstation has remaining preset parallel resources, multiple test experiments can be performed in parallel. When the preset consumption amount for each test experiment is less than the remaining preset parallel resources of the current workstation, the test can proceed smoothly until the current test is completed. The total number of tests running in parallel at each workstation must not exceed the preset parallel resources.
8. An automatic scheduling system for assembly line experiments, characterized in that, include: The initial population generation module is used to randomly generate a permutation array as the initial population, wherein the permutation array represents the different detection orders of each detection experiment, and each detection order is an individual in the initial population; The first offspring determination module is used to perform a crossover operation on the initial population as the parent generation to determine the first offspring. The second offspring determination module is used to pair individuals in the initial population, determine the paired individuals, and use the paired individuals as the parents to perform mutation operations to determine the second offspring; wherein, the probability of linked genes in biological genetics is introduced to perform mutation operations on the parents. The target population determination module is used to determine the target population based on the first offspring, the second offspring, and the parent generation; The first total detection time determination module is used to perform detection according to the detection order corresponding to each individual in the target population and determine the first total detection time corresponding to each individual. The detection module is used to select individuals that meet the first preset requirements in the first total detection time as target individuals, and to perform detection on each detection experiment according to the detection order corresponding to the target individuals.
9. A computing device, comprising a memory, a processor, and a program stored in the memory and running on the processor, characterized in that, When the processor executes the program, it implements the steps of the automatic scheduling method for pipeline experiments as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a terminal device, cause the terminal device to perform the steps of the automated scheduling method for pipeline experiments as described in any one of claims 1-7.