Automated handling system and control method, apparatus, storage medium therefor

Abstract

An automatic handling system and a control method, device and storage medium thereof. The method comprises: acquiring information related to cranes and tracks on the automatic handling system; mapping the acquired information to a multi-dimensional space to obtain an initial population; predicting the paths and speeds of the cranes on the automatic handling system based on the initial population by using a genetic algorithm; and controlling the automatic handling system based on the prediction result. The above scheme can improve the handling efficiency of the automatic handling system.

Description

Technical Field

[0001] This invention relates to the field of semiconductor technology, and more specifically to an automated handling system and its control method, apparatus, and storage medium. Background Technology

[0002] Integrated circuit chips, often referred to as "industrial grains," are miniature electronic devices or components that integrate a number of commonly used electronic components (such as transistors, resistors, capacitors, etc.) and their interconnections using semiconductor technology to achieve specific circuit functions.

[0003] In semiconductor manufacturing, overhead hoist transfer (OHT) systems are used. OHT is an automated material handling system in semiconductor manufacturing plants. By installing tracks and cranes on the ceiling, the cranes can transport materials along the tracks. The design of the crane track path and the operating speed of the cranes determine the material handling efficiency and affect production capacity.

[0004] With the continuous development of the semiconductor industry, manufacturers face the challenge of improving production efficiency and reducing costs. As a crucial connecting system in the entire processing, overhead cranes are highly susceptible to congestion or collisions during operation, which severely impacts material handling efficiency. This necessitates manual handling, affecting not only production capacity but also increasing labor costs. Therefore, improving material handling efficiency is imperative. Summary of the Invention

[0005] The problem this invention aims to solve is: how to improve the handling efficiency of automated handling systems.

[0006] To address the above problems, embodiments of the present invention provide a control method for an automated handling system, the method comprising:

[0007] Obtain information related to the overhead crane and tracks of the automated handling system;

[0008] The acquired information is mapped to a multidimensional space to obtain the initial population;

[0009] Based on the initial population, a genetic algorithm is used to predict the path and speed of each crane on the automated transport system.

[0010] The automated handling system is controlled based on the prediction results.

[0011] In one possible embodiment, obtaining information related to the overhead crane and track of the automated transport system includes:

[0012] The speed and track information of each crane on the automated transport system are obtained within a preset historical time period.

[0013] In one possible embodiment, mapping the acquired information to a multidimensional space to obtain an initial population includes:

[0014] The speed and track information of each crane in the automated transport system within a preset historical time period are mapped to a multi-dimensional space to obtain initial individual information. Each initial individual information includes: crane identification information, speed information, and track information.

[0015] The initial individual information is filtered to obtain the individual information of the initial population.

[0016] In one possible embodiment, predicting the path and speed of each crane on the automated transport system using a genetic algorithm based on the initial population includes:

[0017] A selection operation is performed on the initial population to obtain information on the selected individuals;

[0018] Perform a crossover operation on the selected individual information to obtain the crossover individual information;

[0019] Determine if mutation is needed;

[0020] Perform mutation operations on the crossover individuals that need to be mutated to obtain the mutated individual information;

[0021] The mutated individual information is used as the initial individual information of the population in the next iteration process. The selection, crossover and mutation operations are repeated until no mutation is needed. The predicted path information and predicted speed information of each crane are then output.

[0022] In one possible embodiment, performing a selection operation on the initial population to obtain information on the selected individuals includes:

[0023] Calculate the fitness of each individual in the initial population;

[0024] Based on an individual's fitness, the probability of that individual's traits being passed on to the next generation is obtained;

[0025] Individuals whose probability of being passed on to the next generation is greater than a preset probability value are selected as the individual information.

[0026] In one possible embodiment, performing a crossover operation on the selected individual information to obtain the crossover individual information includes:

[0027] A binary-coded uniform crossover method is used to perform crossover operations on the selected individual information.

[0028] In one possible embodiment, performing a mutation operation on the crossover-adjusted individual information to obtain mutated individual information includes:

[0029] Based on the individual information after the intersection, predict the probability of collision between overhead cranes;

[0030] For overhead cranes with a collision probability greater than a preset probability threshold, the speed is changed, and the collision probability is re-predicted based on the changed speed, until the re-predicted collision probability is less than or equal to the preset probability threshold.

[0031] Based on the individual information corresponding to the collision probability that is less than or equal to the preset probability threshold, the mutated individual information is obtained.

[0032] In one possible embodiment, before controlling the automated handling system based on the prediction results, the method further includes:

[0033] Based on the prediction results, a scattered simulation is performed on the overhead crane and track of the automated transport system to verify whether the prediction results are the optimal solution.

[0034] This invention also provides a control device for an automated handling system, the device comprising:

[0035] The acquisition unit is suitable for acquiring information related to the overhead crane and tracks of the automated handling system.

[0036] The initial population establishment unit is suitable for mapping the acquired information to a multi-dimensional space to obtain the initial population;

[0037] The prediction unit is adapted to predict the path and speed of each crane on the automated transport system based on the initial population using a genetic algorithm.

[0038] The control unit is adapted to control the automated handling system based on the prediction results.

[0039] This invention also provides an automated handling system, which includes the control device for the automated handling system described above.

[0040] This invention also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of any of the methods described above.

[0041] This invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the steps of any of the methods described above when running the computer program.

[0042] Compared with the prior art, the technical solution of the embodiments of the present invention has the following advantages:

[0043] By applying the scheme of this invention, after obtaining relevant information about the overhead cranes and tracks on the automated transport system, an initial population is first obtained. Then, a genetic algorithm is used to predict the path and speed of each overhead crane on the automated transport system. Finally, the automated transport system is controlled based on the prediction results. Since the genetic algorithm can select the most adapted individuals from the initial population, the most suitable crane path and speed for the automated transport system can be obtained based on the genetic algorithm, thereby minimizing congestion or collisions during crane operation and improving transport efficiency. Attached Figure Description

[0044] Figure 1 This is a flowchart of a control method for an automated handling system according to an embodiment of the present invention;

[0045] Figure 2 This is a schematic diagram of a partial structure of an automated handling system;

[0046] Figure 3 This is a flowchart of another control method for an automated handling system in an embodiment of the present invention;

[0047] Figure 4 This is a scatter plot of a speed prediction result in one embodiment of the present invention;

[0048] Figure 5 This is a schematic diagram of the structure of a control device for an automatic handling system according to an embodiment of the present invention. Detailed Implementation

[0049] In automated material handling systems, overhead cranes serve as a crucial connecting system throughout the entire processing. If the overhead crane encounters congestion or collisions during its operation, it will severely impact material handling efficiency.

[0050] To address this problem, this invention provides a control method for an automated handling system. This method obtains an initial population by acquiring information about the overhead cranes and tracks within the automated handling system. A genetic algorithm is then used to predict the paths and speeds of each crane on the system, allowing for control of the automated handling system based on the predictions. Since the genetic algorithm can select the most adapted individuals, the predictions obtained can minimize congestion or collisions during crane operation, thereby improving handling efficiency.

[0051] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0052] Reference Figure 1 This invention provides a control method for an automated handling system, the method including the following steps:

[0053] Step 11: Obtain information related to the overhead crane and track of the automated transport system.

[0054] In practical implementation, obtaining information related to the overhead cranes and tracks of the automated transport system can include: acquiring the speed information and track information of each overhead crane on the automated transport system within a preset historical time period. The preset historical time period can be set according to actual needs; for example, it can be set to the past year. In this case, the acquired information will be the speed information and track information of the overhead cranes on the automated transport system over the past year.

[0055] It should be noted that automated handling systems typically have multiple overhead cranes. Within a preset historical time period, each crane may travel on multiple tracks, and the same crane may also have multiple speeds while traveling on the same track. Therefore, each crane can have multiple speed information and multiple track information.

[0056] For example, in Figure 2 The schematic diagram of a partial structure of the automated handling system shows 12 overhead cranes (as shown in pink) and multiple tracks (as shown by blue dashed lines). Over the past year, the tracks traveled by crane 201 include: track s1, track s2, and track s3; the tracks traveled by crane 202 include: track s5, track s1, and track s4. Crane 201 travels at a speed of v1 or v2 on track s1. Crane 202 travels at a speed of v3 on track s4 and at a speed of v4 on track s1.

[0057] Step 12: Map the acquired information to a multidimensional space to obtain the initial population.

[0058] Specifically, the speed and track information of each overhead crane in the automated transport system within a preset historical time period can be mapped to a multi-dimensional space to obtain initial individual information. This initial individual information is then filtered to obtain the individual information of the initial population. Each initial individual information includes: crane identification information, speed information, and track information. The track information can include straight track information, curved track information, and information on the intersection of straight and curved tracks.

[0059] In practical implementation, the multi-dimensional space refers to a three-dimensional space established using crane markers, speed parameters, and track markers. For example, refer to... Figure 2 When the overhead crane 202 travels at a speed of v3 on track s4, the initial individual information obtained after mapping to multidimensional space can be represented as (202, v3, s4). In this way, by mapping each overhead crane, its track, and its speed on each track to multidimensional space, multiple initial individual information can be obtained.

[0060] In practice, when screening initial individual information, a speed screening range can be set based on the maximum permissible speed of the overhead crane on the automated transport system. The initial individual information corresponding to the speed that meets the speed screening range can be used as the individual information of the initial population.

[0061] For example, assuming the maximum permissible speed of the overhead crane on this automated transport system is 100 m / min, a speed filtering interval can be set to (0, 80 m / min). The speed values ​​in the initial individual information are then matched against this speed filtering interval. If the speed value of an initial individual falls within this speed filtering interval, that initial individual is considered part of the initial population and can continue with subsequent operations. Initial individuals that do not fall within this speed filtering interval are filtered out.

[0062] It should be noted that the maximum value of the speed screening range is usually less than the maximum allowable speed of the overhead crane on the automated transport system. This allows the initial individual information with lower speeds to be screened out for subsequent operations. In this way, the actual speed of the overhead crane on the automated transport system is less than the maximum allowable speed, which can further reduce the occurrence of congestion or collisions during the operation of the overhead crane and ensure compatibility with other control programs of the automated transport system.

[0063] Step 13: Based on the initial population, use a genetic algorithm to predict the path and speed of each crane on the automated transport system.

[0064] Genetic algorithms are a search optimization method that simulates the heredity and evolution of organisms in nature. Based on Darwin's principle of natural selection and genetic mechanisms, they consist of three stages: selection, crossover, and mutation.

[0065] When using genetic algorithms to predict the paths and speeds of overhead cranes in an automated material handling system (AWSS), a genetic algorithm can be used to start from an initial population. Through selection, crossover, and mutation operations, the fitness of individuals in the population is continuously optimized, producing generations of individuals that are better adapted to the environment, eventually converging to obtain the optimal solution to the problem. The optimal solution refers to the situation where all overhead cranes in the AWSS travel on the predicted tracks without waiting or colliding, thereby maximizing crane efficiency.

[0066] Step 14: Control the automated handling system based on the prediction results.

[0067] In practice, after obtaining the predicted paths and speeds of each crane on the automated transport system, the cranes can be controlled to move on the automated transport system based on these predicted results.

[0068] By using genetic algorithms to predict the paths and speeds of each crane in an automated transport system, the final prediction results can ensure that the cranes travel on the predicted tracks without waiting or colliding, thereby improving transport efficiency.

[0069] Figure 3 This is a flowchart of an automated handling system control method according to another embodiment of the present invention. (Refer to...) Figure 3 The method may include:

[0070] Step 31: Obtain initial individual information.

[0071] In practical implementation, the speed and track information of each overhead crane on the automated transport system within a preset historical time period can be mapped to a multi-dimensional space to obtain initial individual information. Each initial individual information includes: crane identification information, speed information, and track information. The track information may include straight track information, curved track information, and information on the intersection of straight and curved tracks.

[0072] Step 32: Based on the initial individual information, obtain the individual information of the initial population.

[0073] In practice, a preset speed filtering interval can be used to filter the initial individual information to obtain the individual information of the initial population.

[0074] It should be noted that in practical applications, the initial population size can be preset, and the initial individual information can be filtered using a preset speed filtering interval. If the number of filtered individuals is less than the preset value, the speed filtering interval can be increased to ensure the number of filtered individuals meets the requirement. If the number of filtered individuals is greater than the preset value, the speed filtering interval can be decreased to ensure the number of filtered individuals meets the requirement. This ensures that the initial population size is sufficient to generate the optimal solution.

[0075] For steps 31 and 32, please refer to the description of step 12 above, which will not be repeated here.

[0076] After obtaining the information of all individuals in the initial population, a genetic algorithm is used to iterate through this information, thereby predicting the path and speed of each crane on the automated transport system. Each iteration may include steps 33 to 36. Specifically:

[0077] Step 33: Perform a selection operation on the initial population to obtain the information of the selected individuals.

[0078] Specifically, the fitness of each individual in the initial population can be calculated first, and then the probability of an individual passing on to the next generation can be obtained based on the individual's fitness. Finally, the information of individuals whose probability of passing on to the next generation is greater than a preset probability value is used as the selected individual information.

[0079] Assuming the initial population contains n individuals, the fitness of each individual is calculated using the individual fitness calculation method in genetic algorithms, where n is a positive integer. Let the fitness of the i-th individual be f. i If i ≤ n, then formula (1) can be used to obtain the probability P of the i-th individual being inherited by the next generation. i :

[0080]

[0081] Where, ∑f i This represents the sum of the fitness of n individuals.

[0082] Therefore, using formula (1), we can obtain the probability that each of the n individuals will be passed on to the next generation.

[0083] The probability of each individual passing on to the next generation is compared with the preset probability value P. th In comparison, when the probability of this individual inheriting the gene to the next generation is greater than P... th When this condition is met, it indicates that the individual has high fitness. This individual is then used as the parent, or the selected individual, and step 34 is executed. For example, if the initial population has 20 individuals, the number of selected individuals can be 15.

[0084] By performing selection operations on the initial population, we can avoid getting stuck in local optima during the prediction process using genetic algorithms and maintain population diversity.

[0085] Step 34: Perform a crossover operation on the selected individual information to obtain the crossover individual information.

[0086] In practice, the crane and track information of all selected individuals can be merged pairwise to obtain the cross-referenced individual information. When merging each crane and track pairwise, different encoding methods have different cross-reference methods to match them.

[0087] In one embodiment of the present invention, a binary encoding uniform crossover method can be used to perform the crossover operation on the selected individual information. Specifically, each crane and each track can be binary encoded separately, and then the encoded cranes and tracks can be uniformly crossovered, that is, the cranes and tracks in the selected individual information can be paired and matched to form the crossover individual information based on speed and track. The number of crossover individuals is greater than the number of selected individuals.

[0088] For example, if the first selected individual information is (202, v3, s4) and the second selected individual information is (201, v2, s1), then after uniform cross-coding of the binary codes, the cross-generated individual information can include: (202, v3, s4), (202, v3, s1), (201, v2, s1), (201, v2, s4).

[0089] By merging the selected individuals' cranes and tracks in pairs, the number of individuals available for mutation operations can be increased, making it easier to predict the optimal speed and optimal path for each crane through subsequent mutation operations.

[0090] Step 35: Determine if mutation is needed.

[0091] Specifically, based on the individual information after the crossing, it is possible to determine whether mutation is needed, that is, whether the speed needs to be changed, by predicting the collision probability between the cranes.

[0092] In practice, when predicting collisions between individuals after an intersection, pairwise predictions can be made for overhead cranes on the same track to obtain their collision probabilities. If the collision probability is greater than a preset probability threshold, mutation is required; otherwise, mutation is not necessary.

[0093] In practice, when at least one of the overhead cranes requiring collision prediction needs to mutate, it indicates that at least one overhead crane in the automated transport system needs to wait or collide with other overhead cranes while traveling. In this case, proceed to step 36. When none of the overhead cranes requiring collision prediction need to mutate, it indicates that none of the overhead cranes in the automated transport system need to wait or collide with other overhead cranes while traveling. Proceed to step 37.

[0094] Step 36: Perform mutation operation on the crossover individual information that needs to be mutated to obtain the mutated individual information.

[0095] Specifically, based on the individual information after the intersection, after predicting the collision probability between overhead cranes, the speed of overhead cranes with a collision probability greater than a preset probability threshold is changed, and the collision probability (also called the mutation probability) is re-predicted based on the changed speed, until the re-predicted collision probability is less than or equal to the preset probability threshold. Finally, the mutated individual information is obtained based on the individual information corresponding to the collision probabilities less than or equal to the preset probability threshold.

[0096] If the probability of a collision between the two overhead cranes exceeds a preset probability threshold, the speed of either crane can be changed. New individual information is then generated using the changed speed, and a new collision prediction is performed. Specifically, when changing the crane speed, other speed information of the same crane can be arbitrarily selected from the initial individual information to form new individual information for that crane.

[0097] For example, refer to Figure 2 Assuming that after the intersection, cranes 201 and 202 correspond to the same track s1, the collision probability of cranes 201 and 202 on track s1 can be calculated. If the collision probability is greater than a preset probability threshold, the speed of crane 201 can be changed, the speed of crane 202 can be changed, or both cranes 201 and 202 can be changed.

[0098] Taking the change of the speed of crane 201 as an example, other speed values ​​of crane 201 are found from the initial individual information. Based on the crane 201's identifier, the changed speed, and track s1, new individual information is formed, and collision prediction is performed again. If the collision probability obtained after the second collision prediction is still greater than the preset probability threshold, other speed values ​​of crane 201 need to be found again from the initial individual information. Based on the crane 201's identifier, the changed speed, and track s1, new individual information is formed again, and collision prediction is performed again. The mutation stops when the collision probability of cranes 201 and 202 on track s1 is less than or equal to the preset probability threshold, and the corresponding individual information of crane 201 at this time is taken as the new individual information of crane 201.

[0099] In practical implementation, an adaptive mutation method can be used to calculate the collision probability (also known as the mutation probability) after the speed change. Specifically, assuming that the individual after the m-th crossover is mutated, where m is a positive integer, the mutation probability P' of the individual after the m-th crossover can be obtained using formula (2). m :

[0100]

[0101] Where K1 and K2 are constants in the interval [0, 1] of nature. max f represents the maximum fitness of individuals after all crossovers. g Let f represent the average fitness of all individuals after crossover. Let f represent the fitness of the individual after the mutation following the m-th crossover.

[0102] The individual information obtained after the mutation operation is completed is called the mutated individual information. The mutated individual information refers to the individual information corresponding to a collision probability less than or equal to the preset probability threshold after performing collision prediction on the crossover individuals.

[0103] Step 37: Use the mutated individual information as the initial population individual information in the next iteration process.

[0104] Specifically, after obtaining the information of the mutated individuals, the information of the mutated individuals is used as the information of the initial population in the next iteration process. The selection operation, crossover operation and mutation operation are repeatedly executed until no mutation is needed, that is, all the overhead cranes on the automated transport system do not need to wait or collide with other overhead cranes.

[0105] Step 38: Output the predicted path information and predicted speed information for each crane.

[0106] In practice, during a certain iteration process, when all the individual information after the crossover does not need to be mutated, that is, when the speed of each crane after the crossover operation does not need to be changed, the speed information and track information of the crane in the individual information after the crossover at this time are used as the prediction result of the crane.

[0107] Step 39: Based on the prediction results, control the automated handling system.

[0108] That is, the speed and track information output in step 38 are used to control the movement of each crane in the automated transport system.

[0109] Using the control method of the automatic handling system in the embodiments of the present invention, for Figure 2 The speeds of the 12 overhead cranes on tracks s1 to s12 were predicted, and the prediction results are shown in Table 2.

[0110] Table 2

[0111]

[0112] In some embodiments, before performing step 39, a scatter simulation can be performed on the overhead crane and track of the automated transport system based on the prediction results to verify whether the prediction results are the optimal solution.

[0113] Specifically, a scatter plot was used to simulate the speeds of 12 overhead cranes on 12 tracks in the automated transport system. The resulting scatter plot is shown below. Figure 4 As shown. (Refer to...) Figure 4 The horizontal axis represents the 12 tracks, and the vertical axis represents the speed of the overhead cranes traveling on those tracks. No collision is defined as no overlap in the speeds of the cranes on the same track; by default, the cranes do not stop. Speed ​​control maximizes crane efficiency. Figure 4 It can be seen that none of the 12 cranes on each track collided, proving that the prediction result at this time is the optimal solution. Using this optimal solution to control the allowable operation of each crane on the automated transport system can make the efficiency of the automated transport system optimal.

[0114] Using the solution of this invention, as the number of products and equipment increases, the number of overhead cranes increases accordingly, and the tracks become more complex. Based on the genetic algorithm, the population size is continuously changed, and crossover mutation is used to predict the best path and the optimal crane speed, thereby achieving the optimal handling efficiency.

[0115] To enable those skilled in the art to better understand and implement the present invention, the apparatus, testing system, electronic device, and computer-readable storage medium corresponding to the above method are described in detail below.

[0116] Reference Figure 5 This invention also provides a control device 50 for an automated transport system, which may include: an acquisition unit 51, an initial population establishment unit 52, a prediction unit 53, and a control unit 54. Wherein:

[0117] The acquisition unit 51 is adapted to acquire information related to the overhead crane and track of the automated transport system.

[0118] The initial population establishment unit 52 is adapted to map the acquired information to a multi-dimensional space to obtain an initial population;

[0119] The prediction unit 53 is adapted to predict the path and speed of each crane on the automated transport system based on the initial population using a genetic algorithm.

[0120] The control unit 54 is adapted to control the automated handling system based on the prediction results.

[0121] The acquisition unit 51, the initial population establishment unit 52, the prediction unit 53, and the control unit 54 can be implemented with reference to the above description of the control method for the automatic transport system, and will not be repeated here.

[0122] This invention also provides an automated handling system, which includes the control device 50 of the aforementioned automated handling system.

[0123] Using the control device 50 of the automated transport system in this embodiment of the invention, the overhead crane and track of the automated transport system are first mapped to a multi-dimensional space to establish an initial population. Through selection and crossover, crossover individuals are obtained. Subsequent crossover individuals are used for crane collision prediction analysis, and the optimal solution is achieved through mutation rate. The initial population uses the overhead crane and track as samples. The mutation is based on the predicted collision probability to determine whether a speed change is needed, thereby determining the data output. The optimal result is that the scattered points do not converge.

[0124] During the crossover process, the speed of the trolleys is predicted by combining the data from the overhead cranes and the tracks in pairs. The optimal individuals from these pairs are then compared to predict collisions and determine if mutation is necessary. The final output, representing the speed of all overhead cranes on their tracks, is obtained when all trolleys travel on their tracks without waiting or colliding, thus maximizing trolley efficiency.

[0125] This invention also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of any of the above methods.

[0126] In specific implementations, the computer-readable storage medium may include ROM, RAM, disk, or optical disk, etc.

[0127] This invention also provides an electronic device, which includes a memory and a processor. The memory stores a computer program that can run on the processor, and when the processor runs the computer program, it performs the steps of any of the methods described above.

[0128] Regarding the modules / units included in the various devices and products described in the above embodiments, they can be software modules / units, hardware modules / units, or a combination of both. For example, for various devices and products applied to or integrated into a chip, all of their modules / units can be implemented using hardware methods such as circuits, or at least some modules / units can be implemented using software programs that run on a processor integrated within the chip, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits; for various devices and products applied to or integrated into a chip module, all of their modules / units can be implemented using hardware methods such as circuits, and different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components of the chip module, or at least some modules / units can be implemented using hardware methods such as circuits. The components can be implemented using software programs that run on the processor integrated within the chip module. The remaining (if any) modules / units can be implemented using hardware methods such as circuits. For various devices and products applied to or integrated into the terminal, each of its components / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or in different components within the terminal. Alternatively, at least some modules / units can be implemented using software programs that run on the processor integrated within the terminal, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits.

[0129] While the present invention has been disclosed above, it is not limited thereto. Any person skilled in the art can make various modifications and alterations without departing from the spirit and scope of the invention; therefore, the scope of protection of the present invention should be determined by the scope defined in the claims.

Claims

1. A control method for an automated handling system, characterized in that, include: Obtain information related to the overhead crane and tracks of the automated handling system; The acquired information is mapped to a multidimensional space to obtain the initial population; Based on the initial population, a genetic algorithm is used to predict the path and speed of each crane on the automated transport system. The automated handling system is controlled based on the prediction results.

2. The control method for the automated handling system as described in claim 1, characterized in that, The acquisition of information related to the overhead crane and track of the automated transport system includes: The speed and track information of each crane on the automated transport system are obtained within a preset historical time period.

3. The control method for the automated handling system as described in claim 2, characterized in that, The process of mapping the acquired information to a multidimensional space to obtain an initial population includes: The speed and track information of each crane in the automated transport system within a preset historical time period are mapped to a multi-dimensional space to obtain initial individual information. Each initial individual information includes: crane identification information, speed information, and track information. The initial individual information is filtered to obtain the individual information of the initial population.

4. The control method for the automated handling system as described in claim 1, characterized in that, The step of predicting the path and speed of each crane on the automated transport system using a genetic algorithm based on the initial population includes: A selection operation is performed on the initial population to obtain information on the selected individuals; Perform a crossover operation on the selected individual information to obtain the crossover individual information; Determine if mutation is needed; Perform mutation operations on the crossover individuals that need to be mutated to obtain the mutated individual information; The mutated individual information is used as the initial individual information of the population in the next iteration process. The selection, crossover and mutation operations are repeated until no mutation is needed. The predicted path information and predicted speed information of each crane are then output.

5. The control method for the automated handling system as described in claim 4, characterized in that, The step of performing a selection operation on the initial population to obtain information on the selected individuals includes: Calculate the fitness of each individual in the initial population; Based on an individual's fitness, the probability of that individual's traits being passed on to the next generation is obtained; Individuals whose probability of being passed on to the next generation is greater than a preset probability value are selected as the individual information.

6. The control method for the automated handling system as described in claim 4, characterized in that, The step of performing a crossover operation on the selected individual information to obtain the crossover individual information includes: A binary-coded uniform crossover method is used to perform crossover operations on the selected individual information.

7. The control method for the automated handling system as described in claim 4, characterized in that, The step of performing a mutation operation on the crossover-adjusted individual information to obtain mutated individual information includes: Based on the individual information after the intersection, predict the probability of collision between overhead cranes; For overhead cranes with a collision probability greater than a preset probability threshold, the speed is changed, and the collision probability is re-predicted based on the changed speed until the re-predicted collision probability is less than or equal to the preset probability threshold; based on the individual information corresponding to the collision probabilities less than or equal to the preset probability threshold, the mutated individual information is obtained.

8. The control method for the automated handling system as described in claim 1, characterized in that, Before controlling the automated handling system based on the prediction results, the following steps are also included: Based on the prediction results, a scattered simulation is performed on the overhead crane and track of the automated transport system to verify whether the prediction results are the optimal solution.

9. A control device for an automated handling system, characterized in that, include: The acquisition unit is suitable for acquiring information related to the overhead crane and tracks of the automated handling system. An initial population establishment unit is adapted to map the acquired information to a multi-dimensional space to obtain an initial population; a prediction unit is adapted to predict the path and speed of each crane on the automated transport system based on the initial population using a genetic algorithm. The control unit is adapted to control the automated handling system based on the prediction results.

10. An automated handling system, characterized in that, Includes the control device for the automated handling system as described in claim 9.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program is executed by a processor to implement the steps of the method according to any one of claims 1 to 8.

12. An electronic device comprising a memory and a processor, wherein the memory stores a computer program capable of running on the processor, characterized in that, When the processor runs the computer program, it performs the steps of the method according to any one of claims 1 to 8.

Images