Flexible open factory scheduling method and system, terminal and storage medium

Abstract

The invention relates to a flexible open factory scheduling method and system, a terminal and a storage medium, and relates to the field of production activity planning, and the method comprises the steps: obtaining a workpiece image of a workpiece; processing duration is matched from a preset processing duration matching model according to the workpiece image; calculating a quotient of the processing duration and a preset completion duration, and defining the quotient as a duration utilization rate; when the duration utilization rate is greater than the preset workshop utilization rate, matching a redistribution step from a preset workpiece redistribution model according to the processing duration; according to the redistribution step, a preset carrying device is controlled to redistribute the workpieces into the workshops; when the duration utilization rate is not greater than the preset workshop utilization rate, matching a workshop number from a preset workshop number matching model according to the duration utilization rate; and controlling a preset carrying device to convey the workpiece into the workshop for processing according to the workshop number. The method has the effects of improving the production efficiency of a workshop and reducing the completion time.

Description

Technical Field

[0001] The present invention relates to the field of production activity planning, and in particular to a flexible open factory scheduling method, system, terminal and storage medium. Background Art

[0002] Flexible open workshop scheduling is to integrate and utilize workshops or resources in different regions, give full play to the advantages of each region, and improve resource utilization.

[0003] In the existing technology, flexible open workshop scheduling is widely used in the production process of intelligent workshops in the manufacturing industry, scattered testing workshops in various places, and cross-regional distribution services. Flexible workshop scheduling is a multi-workshop scheduling problem. Each workshop can be used as a flexible operation workshop. It is necessary to consider the collaborative production of multiple workshops. Flexible open workshop scheduling is used to reduce the completion time. The completion time depends on the workshop that takes the longest time to complete the workpiece processing.

[0004] When multiple workpieces are dispatched to the same workshop, it is easy for the workshop to take longer to process the workpieces, which in turn leads to a longer completion time, which in turn causes other workshops to be idle for a longer time and reduces production efficiency. Summary of the invention

[0005] In order to improve the production efficiency of a workshop and reduce the completion time, the present invention provides a flexible open factory scheduling method, system, terminal and storage medium.

[0006] In a first aspect, the present invention provides a flexible open factory scheduling method, which adopts the following technical solution:

[0007] A flexible open factory scheduling method, comprising:

[0008] acquiring a workpiece image of the workpiece;

[0009] Matching the processing time from a preset processing time matching model according to the workpiece image;

[0010] Calculate the quotient of processing time and preset completion time and define it as time utilization rate;

[0011] When the time utilization is greater than the preset workshop utilization, a redistribution step is matched from a preset workpiece redistribution model according to the processing time;

[0012] Controlling a preset carrier to redistribute the workpieces into the workshop according to the redistribution steps;

[0013] When the time utilization is not greater than the preset workshop utilization, the workshop number is matched from the preset workshop number matching model according to the time utilization;

[0014] According to the workshop number, the preset carrier is controlled to transport the workpiece to the workshop for processing.

[0015] By adopting the above technical solution, the occupancy rate of the processing time to the workshop can be displayed through the time utilization rate, and when the time utilization rate is too high, the workpieces can be reallocated to reduce the completion time, thereby improving the production efficiency of the workshop.

[0016] Optionally, it also includes a machine position scheduling method, and the machine position scheduling method includes:

[0017] Calculate the quotient of the processing time and the preset operating time and define it as the machine utilization rate;

[0018] When the machine utilization rate is greater than the preset operation utilization rate, the processing time is defined as the operation time;

[0019] Based on the situation that the machine position utilization rate is not greater than the preset operation utilization rate, the processing process and the process duration corresponding to the processing process are matched from the preset process recognition model according to the workpiece image;

[0020] Matching the process allocation plan from the preset process matching model according to the running time, processing process and process duration;

[0021] According to the process allocation plan, the preset processing device is controlled to process the workpiece, and the process allocation plan is displayed through a preset plan display method.

[0022] By adopting the above technical solution, the time required for complete processing of the workpiece is displayed as a function of the occupancy rate of the processing equipment through the machine position utilization rate. When the occupancy rate is too high, the workpiece process is allocated based on the time required for complete processing of the workpiece, so that the processes are evenly distributed on different processing equipment, thereby reducing the completion time and improving the production efficiency of the workshop.

[0023] Optionally, a workpiece scheduling method is also included, and the workpiece scheduling method includes:

[0024] Matching a priority number from a preset priority algorithm according to the workpiece image;

[0025] When the priority number falls within a preset priority range, the workpiece position is matched from a preset workpiece position recognition model according to the workpiece image;

[0026] Matching the take-off stroke from a preset take-off stroke matching model according to the position of the workpiece;

[0027] Controlling the preset suspension bridge device according to the take-off stroke to transport the workpiece onto the suspension bridge and take it away from the preset conveying device;

[0028] Matching a priority position from a preset priority position matching model according to the priority number;

[0029] Matching a placement trip from a preset placement trip matching model according to the priority position;

[0030] The preset suspension bridge device is controlled according to the placement stroke to transport the workpiece to the preferred position.

[0031] By adopting the above technical solution, workpieces with higher priority numbers are taken out from the conveying device and moved forward through the suspension bridge device, so that the processing device processes the parts in sequence according to the priority number, thereby improving the efficiency of workpiece processing.

[0032] Optionally, the workpiece scheduling method further includes:

[0033] When the priority number falls within a preset priority range, obtaining a position image of the priority position;

[0034] Judging whether there is space for placing the workpiece at the priority position from a preset workpiece position judgment model according to the workpiece image and the position image;

[0035] When there is no space for the workpiece to be placed in the priority position, the length of the workpiece is identified from a preset workpiece length identification model according to the workpiece image;

[0036] identifying a workpiece gap from a preset workpiece gap recognition model according to the position image;

[0037] Matching the adjustment length from a preset adjustment length recognition model according to the workpiece length and the workpiece gap;

[0038] Calculating the quotient of the adjustment length and the preset conveying speed of the conveying device and defining the quotient as the adjustment time length;

[0039] Matching the blocking position from a preset blocking position recognition model according to the position image;

[0040] Matching a blocking stroke from a preset blocking stroke matching model according to the blocking position and the adjustment duration;

[0041] The preset suspension bridge device is controlled according to the blocking stroke to block the workpiece after the priority position so that the workpiece after the priority position moves backward.

[0042] By adopting the above technical solution, when the suspension bridge device takes out the workpiece from the conveying device, the suspension bridge device moves synchronously with the conveying device to reduce the backward movement of the workpiece. When the suspension bridge device puts the workpiece into the conveying device, the suspension bridge device moves asynchronously with the conveying device to make the suspension bridge device press against the workpiece after the priority position, thereby forcing the workpiece to move backward.

[0043] Optionally, the workpiece scheduling method further includes a gap adjustment method, and the gap adjustment method includes:

[0044] After the workpiece is moved backward by the suspension bridge device, a backward moving image between the workpiece position and the priority position is acquired;

[0045] judging whether the gap between the workpieces exceeds the preset workpiece gap from a preset workpiece gap judging model according to the backward-moved image;

[0046] When the gap between the workpieces does not exceed a preset workpiece gap, identifying workpiece features from a preset workpiece feature recognition model according to the backward-shifted image;

[0047] Matching the adjustment stroke from a preset gap adjustment model based on the workpiece characteristics;

[0048] The preset gap adjustment device is controlled according to the adjustment stroke to adjust the gap between the workpieces.

[0049] By adopting the above technical solution, a certain gap needs to be left between the workpieces to facilitate the processing of the workpieces. When the suspension bridge device forces the workpieces to move backward, it is easy to reduce or even eliminate the gap between the workpieces after the priority position. The workpieces are separated by the gap adjustment device to maintain a certain gap, thereby improving the efficiency of workpiece processing.

[0050] Optionally, the workpiece scheduling method further includes a workpiece exchange method, and the workpiece exchange method includes:

[0051] When there is no space for the workpiece to be placed in the priority position, the hysteresis series is matched from the preset priority algorithm according to the position image;

[0052] When the hysteresis series falls into a preset hysteresis range, an extraction stroke is matched from a preset extraction stroke matching model according to the workpiece position and the priority position;

[0053] According to the extraction stroke, the preset suspension bridge device is controlled to sequentially extract the workpieces at the workpiece position and the priority position from the preset conveying device;

[0054] Matching the exchange stroke from a preset exchange stroke matching model according to the workpiece position and the priority position;

[0055] The preset suspension bridge device is controlled according to the exchange stroke to place the workpiece on the suspension bridge device in the workpiece position and the priority position in sequence, and the positions of the workpiece at the workpiece position and the priority position are exchanged.

[0056] By adopting the above technical scheme, when the workpiece at the workpiece position and the workpiece at the priority position happen to need to be exchanged, the workpiece at the workpiece position and the workpiece at the priority position are taken out in turn through the suspension bridge device, and then the workpiece at the priority position and the workpiece at the workpiece position are put in in turn through the suspension bridge device, thereby completing the exchange of workpieces.

[0057] Optionally, the workpiece scheduling method further includes a workpiece guiding method, and the workpiece guiding method includes:

[0058] matching the guide position from a preset guide position recognition model according to the workpiece image;

[0059] Matching a guide stroke from a preset guide stroke matching model according to the guide position and the take-away stroke;

[0060] According to the guide stroke, the guide device preset on the suspension bridge device is controlled to lift one end of the workpiece at the guide position to guide the workpiece into the suspension bridge device.

[0061] By adopting the above technical solution, one end of the workpiece is lifted by the guiding device, so that the workpiece is partially separated from the conveying device, thereby facilitating the lifting bridge device to take out the workpiece, thereby reducing the situation where the workpiece and the conveying device are tightly fitted, causing the lifting bridge device to be unable to take out the workpiece.

[0062] In a second aspect, the present application provides a flexible open factory scheduling system, which adopts the following technical solution:

[0063] A flexible open factory scheduling system, comprising:

[0064] An acquisition module, used for acquiring a workpiece image, a position image and a backward movement image;

[0065] A memory for storing a program of a control method of any one of the flexible open factory scheduling methods;

[0066] The program in the memory can be loaded and executed by the processor and realizes any one of the control methods of a flexible open factory scheduling method.

[0067] In a third aspect, the present application provides a computer storage medium capable of storing corresponding programs, which is convenient for implementing a flexible open factory scheduling method, and adopts the following technical solution:

[0068] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any one of the above-mentioned flexible open factory scheduling methods.

[0069] In a fourth aspect, the present application provides an intelligent terminal, which adopts the following technical solution:

[0070] An intelligent terminal comprises a memory and a processor. The memory stores a computer program which can be loaded by the processor and execute any flexible open factory scheduling method.

[0071] In summary, the present application includes at least one of the following beneficial technical effects:

[0072] 1. The utilization rate of the processing time is used to show the occupancy rate of the workshop. When the utilization rate of the processing time is too high, the workpieces are reallocated to reduce the completion time, thereby improving the production efficiency of the workshop;

[0073] 2. The machine utilization rate shows the time required to complete the workpiece processing to the occupancy rate of the processing device. When the occupancy rate is too high, the workpiece process is allocated based on the time required to complete the workpiece processing, so that the process is evenly distributed on different processing devices, thereby reducing the completion time and improving the production efficiency of the workshop;

[0074] 3. The workpieces with higher priority numbers are taken out from the conveying device and moved forward through the suspension bridge device, so that the processing device can process the parts in sequence according to the priority number, thereby improving the efficiency of workpiece processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 It is a flow chart of a flexible open factory scheduling method.

[0076] Figure 2 It is a flow chart of the aircraft scheduling method.

[0077] Figure 3 Is the process of the workpiece scheduling method Figure 1 .

[0078] Figure 4 Is the process of the workpiece scheduling method Figure 2 .

[0079] Figure 5 is a flow chart of the gap adjustment method.

[0080] Figure 6 is a flow chart of the workpiece exchange method.

[0081] Figure 7 is a flow chart of the workpiece guidance method.

[0082] Figure 8 It is a module diagram of a flexible open factory scheduling system. DETAILED DESCRIPTION

[0083] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the following Figure 1-8 It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0084] Reference Figure 1 , the embodiment of the present application discloses a flexible open factory scheduling method, comprising the following steps:

[0085] Step 100: Acquire a workpiece image of a workpiece.

[0086] The workpiece image refers to a picture of the workpiece. The workpiece image can be obtained through a camera. The method for obtaining the workpiece image is selected by the staff according to the actual situation and will not be elaborated here.

[0087] Step 101: Matching the processing time from a preset processing time matching model according to the workpiece image.

[0088] The processing time matching model refers to a neural network model obtained through sample training in advance. The processing time matching model can match the time required to process the workpiece according to the shape of the workpiece shown in the picture. The processing time is the result obtained from the matching of the processing time matching model.

[0089] Step 102: Calculate the quotient of the processing time and the preset completion time, and define it as the time utilization rate.

[0090] Completion time refers to the time required for a workshop to complete the processing of a workpiece. The time required for a single workshop to process a workpiece is defined as the workshop completion time. The completion time depends on the workshop with the longest completion time. This workshop is generally called the key workshop. The way to shorten the completion time is to shorten the workshop completion time of the key workshop. Time utilization refers to the occupancy rate of processing time to completion time.

[0091] Step 103: When the time utilization is greater than the preset workshop utilization, a redistribution step is matched from a preset workpiece redistribution model according to the processing time.

[0092] The workshop utilization rate refers to the limit of the value of the lower time utilization rate. The workshop utilization rate is selected by the staff according to the actual situation and will not be elaborated here. The time utilization rate is greater than the workshop utilization rate, which means that the time utilization rate is higher. It is necessary to reallocate the workpieces to the workshop to reduce the completion time. Since each workpiece can only process one process at the same time, the minimum completion time at this time is the processing time. The workpiece reallocation model refers to a neural network model obtained through sample training in advance. The workpiece reallocation model can reallocate workpieces to the workshop based on the processing time and the shortest completion time, and select the allocation plan that is closest to the existing allocation plan, where the closest means the least steps need to be adjusted. The reallocation step is the result matched from the workpiece reallocation model.

[0093] The artifact redistribution model generally completes the redistribution step through the migration operation, where the migration operation process is as follows: The migration operator is an important operator of the biogeographic optimization algorithm of the double-layer collaborative optimization, which simulates the migration of species between habitats. The migration operation realizes the sharing of information between different habitats. The migration operator is a probability-based operator that mainly calculates the immigration rate and the emigration rate according to the migration model. The migration operator first needs to calculate the habitat H i The immigration rate λ iTo judge H i Whether migration is needed, and then based on the need to perform migration operations, according to the migration rate μ j Select the habitat to be relocated H j .

[0094] The migration model used by the original biogeography optimization algorithm is a linear model. In actual ecosystems, the migration process is much more complicated than that described by the linear model. The sinusoidal migration model is closer to the laws of nature, and the sinusoidal migration model is better than the linear migration model. Therefore, in the algorithm of this chapter, the sinusoidal migration model is used to calculate the immigration rate and emigration rate of each candidate solution. The calculation formula of the sinusoidal migration model is as follows.

[0095]

[0096]

[0097] Where I represents the maximum immigration rate, S k represents the fitness value of the current individual k, S avg represents the average fitness value, and E represents the maximum emigration rate.

[0098] Since the allocation of workpieces in the factory affects the process scheduling results, a small disturbance in the factory code will have a huge impact on the process code and machine code. In addition, the position of the factory code implicitly maps the workpiece serial number. Simply using the migration operation will change the code length and destroy the mapping relationship. Therefore, based on the above characteristics, a double-point replacement migration strategy is designed for the factory code, which randomly selects two non-repeating habitats from the outgoing individuals to replace the habitats at the corresponding positions in the incoming individuals.

[0099] In the distributed scheduling problem, there are sequential constraints between factory allocation and workpiece scheduling, and the factory code needs to be decoded to confirm the factory to which the workpiece is assigned. At present, most algorithms will change the factory code and process code at the same time when destroying, so it is impossible to determine whether the optimization result comes from the optimization of the factory code or the optimization of the process and machine code. Therefore, after the factory code migration operation, the NEH algorithm will be used to search the process code and machine code locally to find a local optimal solution to determine whether the adjustment of the factory code leads to the optimization of the solution. The following two results can be used to determine whether the change of the factory code leads to the optimization of the solution:

[0100] The factory code is changed through the migration operation, while the process code and machine code remain unchanged.

[0101] The factory code is changed through the migration operation, and the NEH algorithm is used to perform local search on the process code and machine code of the new solution and the old solution.

[0102] In order to ensure a better search solution space, if the new solution of any of the above two results is better than the old solution, the change of the factory code of the new solution is considered to be effective, and the change of the factory code of this solution is retained. If the old solution of the above two results is better than the new solution, the old solution is retained.

[0103] After the factory code is determined, the process code and machine code are migrated again, the fitness values ​​of the new solution and the old solution are compared, and the better solution is retained. The steps of the two-layer collaborative optimization of factory code optimization based on crossover and NEH and process code and machine code optimization based on crossover are as follows:

[0104] Step 1: Arrange the solutions in descending order of HSI.

[0105] Step 2: Use the cosine migration model to calculate the individuals that need to migrate in and out, and use the replacement-based migration operation to operate the factory code. The old solution and the generated new solution are recorded as solution 1 and solution 2.

[0106] Step 3: Decompose the codes of Solution 1 and Solution 2 to obtain the process code and machine code of each factory. Re-sort the process codes using the NEH algorithm, and generate new machine codes using the greedy algorithm. The two new solutions generated by Solution 1 and Solution 2 are recorded as Solution 3 and Solution 4.

[0107] Step 4: Condition 1: Solution 2 is better than Solution 1, Condition 2: Solution 4 is better than Solution 3. If any of Condition 1 and Condition 2 is met, Solution 2 is retained, otherwise Solution 1 is retained.

[0108] Step 5: Use replacement-based migration operations to operate on the process encoding and machine encoding of the solution retained in step 4.

[0109] Step 104: According to the reallocation step, the preset carrier is controlled to reallocate the workpieces to the workshop.

[0110] Allocate workpieces according to processing time to reduce completion time, thereby improving workshop production efficiency.

[0111] Step 105: When the duration utilization is not greater than the preset workshop utilization, a workshop number is matched from a preset workshop number matching model according to the duration utilization.

[0112] If the duration utilization rate is not greater than the workshop utilization rate, it means that the duration utilization rate is low at this time, and the workpiece only needs to be allocated to the workshop with a shorter completion time. The workshop number matching model refers to a neural network model obtained through sample training in advance. The workshop number matching model can match the corresponding workshop number according to the duration utilization rate with the workshop completion time tending to the completion time. The workshop number is the result matched from the workshop number matching model.

[0113] Step 106: Control a preset transport device according to the workshop number to transport the workpiece to the workshop for processing.

[0114] The transport device refers to a carrier used to transport workpieces into the workshop. The transport device and its control method are selected by the staff according to actual conditions and will not be elaborated here.

[0115] Reference Figure 2 , the aircraft slot scheduling method includes the following steps:

[0116] Step 200: Calculate the quotient of the processing time and the preset operation time, and define it as the machine position utilization rate.

[0117] The processing device is a device used to process the workpiece. The processing device is selected by the staff according to the actual situation, so it will not be described here. The running time refers to the time required for the processing device to complete all the processes of the workpiece. The running time of a single processing device is defined as the processing running time. The path with the longest processing time in the workshop is called the critical path. The way to shorten the running time is to shorten the processing running time of the critical path. The machine utilization rate refers to the occupancy rate of the processing time to the running time.

[0118] Step 201: When the machine position utilization rate is greater than the preset operation utilization rate, the processing time is defined as the operation time.

[0119] Operation utilization refers to the limit of the value of the lower machine utilization. The operation utilization is selected by the staff according to the actual situation and will not be described here. If the machine utilization is greater than the operation utilization, it means that the machine utilization is high and it is necessary to reallocate the processing equipment to the workpiece process to reduce the processing operation time. Since each workpiece can only process one process at the same time, the minimum value of the processing operation time is the processing time.

[0120] Step 202: Based on the fact that the machine position utilization is not greater than the preset operation utilization, a processing procedure and a process duration corresponding to the processing procedure are matched from a preset process recognition model according to the workpiece image.

[0121] The process recognition model refers to a neural network model obtained through sample training in advance, and the process matching model can identify the processing steps that the workpiece needs to go through and the corresponding process duration from the image.

[0122] Step 203: Match a process allocation plan from a preset process matching model according to the operation time, processing process and process duration.

[0123] The process matching model refers to a neural network model obtained in advance through sample training. The process matching model can reallocate processes to processing equipment based on the running time as the standard and the shortest processing running time as the goal, and select the process allocation plan that is closest to the existing allocation plan, where the closest means the least steps need to be adjusted.

[0124] The process matching model generally allocates processing equipment through mutation operations. The mutation operation process is as follows: In order to more comprehensively search the solution space in each workshop, the workshop number is not mutated, and then the process number and machine number are subjected to exchange-based mutation operations. For the individuals adjusted in the process number, the machine number is adjusted using a greedy parallel machine allocation strategy. If the fitness index of the new solution after mutation is better than the old solution, the new solution replaces the old solution, otherwise the old solution is retained. In biogeography theory, the probability of habitat mutation is inversely proportional to the number of organisms. The probability of mutation in a habitat in equilibrium is small, and the probability of mutation in habitat s is m. s ,The mutation probability formula of the biogeography optimization algorithm of two-layer collaborative optimization is as follows:

[0125]

[0126] Among them, rand represents a random number, e represents the number of iterations, and e max represents the maximum number of iterations, S s represents the fitness value of the habitat, S avg Represents the average fitness value.

[0127] Step 204: Control a preset processing device to process the workpiece according to the process allocation plan, and display the process allocation plan through a preset plan display method.

[0128] The scheme display method refers to the method used to display the process allocation plan for the convenience of staff to view. Generally, the processing arrangement of each processing device in each workshop is displayed in the form of a Gantt chart. The scheme display method is selected by the staff according to the actual situation and will not be elaborated here.

[0129] Reference Figure 3 ,The job scheduling method includes the following steps:

[0130] Step 300: Match a priority number from a preset priority algorithm according to the workpiece image.

[0131] The priority algorithm refers to the method used to calculate the priority number of workpieces. Among different workpieces, the workpieces that need to be processed first have higher priority numbers, and the processes that need to be processed first in the same workpiece have higher priority numbers. The priority algorithm is selected by the staff based on actual conditions and will not be elaborated here.

[0132] Step 301: When the priority number falls within a preset priority range, the workpiece position is matched from a preset workpiece position recognition model according to the workpiece image.

[0133] The priority range refers to the range of priority numbers of workpieces that need to be processed in advance. Generally, the workpiece with the highest priority number is selected. The priority range is selected by the staff according to the actual situation, which will not be elaborated here. The workpiece position recognition model refers to a neural network model obtained through sample training in advance. The workpiece position recognition model can recognize the workpiece position of the workpiece from the picture.

[0134] Step 302: Match the take-off stroke from a preset take-off stroke matching model according to the workpiece position.

[0135] The conveyor device refers to a device used to transport the workpiece to the processing device for the next processing. The suspension bridge device refers to a device used to adjust the position of the workpiece on the conveyor device. The conveyor device and the suspension bridge device are selected by the staff according to the actual situation and will not be described here. The take-off stroke matching model refers to a neural network model obtained through sample training in advance. The take-off stroke matching model can match the take-off stroke of the suspension bridge device taking the workpiece from the workpiece position on the conveyor device.

[0136] Step 303: Control the preset suspension bridge device according to the take-away stroke to transport the workpiece onto the suspension bridge and take it away from the preset conveying device.

[0137] The workpiece is taken out through the suspension bridge device.

[0138] Step 304: Match the priority position from the preset priority position matching model according to the priority number.

[0139] The priority position matching model refers to a neural network model obtained in advance through sample training. The priority position matching model can match the priority position for placing the workpiece according to the priority number so that the workpiece can be processed in advance.

[0140] Step 305: Match the placement itinerary from a preset placement itinerary matching model according to the priority position.

[0141] The placement stroke matching model refers to a neural network model obtained in advance through sample training. The placement stroke matching model can match the placement stroke of the suspension bridge device to place the workpiece on the conveying device.

[0142] Step 306: Control the preset suspension bridge device according to the placement stroke to transport the workpiece to the priority position.

[0143] The workpieces are arranged according to priority numbers through the suspension bridge device, so that the processing device is controlled to process the workpieces according to the priority numbers, thereby improving the processing efficiency.

[0144] Reference Figure 4,The workpiece scheduling method also includes the following steps:

[0145] Step 307: When the priority number falls into the preset priority range, a position image of the priority position is obtained.

[0146] The location image refers to a picture of a priority location. The location image can be obtained through a camera. The method for obtaining the location image is selected by the staff based on actual conditions and will not be elaborated here.

[0147] Step 308: judging whether there is space for placing the workpiece at the priority position from a preset workpiece position judgment model according to the workpiece image and the position image.

[0148] The workpiece position judgment model refers to a neural network model obtained through sample training in advance. The workpiece position judgment model can be used to determine whether the workpiece can be directly placed in the preferred position.

[0149] Step 309: When there is no space for the workpiece to be placed in the priority position, the length of the workpiece is identified from a preset workpiece length identification model according to the workpiece image.

[0150] The absence of space for the workpiece to be placed in the priority position means that the workpiece cannot be directly placed in the priority position. The workpiece length recognition model refers to a neural network model obtained through sample training in advance. The length recognition model can recognize the shortest workpiece length when the workpiece in the picture is placed flat on the conveyor.

[0151] Step 310: Identify the workpiece gap from a preset workpiece gap identification model according to the position image.

[0152] The workpiece gap recognition model refers to a neural network model obtained through sample training in advance. The workpiece gap recognition model can recognize the gap width existing in the priority position in the image. The workpiece gap is the result recognized from the workpiece gap recognition model.

[0153] Step 311: Match the adjustment length from a preset adjustment length recognition model according to the workpiece length and the workpiece gap.

[0154] The adjustment length recognition model refers to a neural network model obtained in advance through sample training. The adjustment length recognition model can identify the adjustment length of the priority position that needs to be adjusted to maintain the processing gap after the workpiece is placed in the priority position according to the pre-set workpiece gap, wherein the workpiece gap refers to the minimum space width between the workpieces to prevent the workpieces from sticking together so as to facilitate the processing of the workpieces one by one by the processing device. The workpiece gap is selected by the staff according to the actual situation and will not be elaborated here.

[0155] Step 312: Calculate the quotient of the adjustment length and the preset transmission speed of the transmission device, and define it as the adjustment duration.

[0156] The conveying speed refers to the speed at which the conveyor conveys the workpieces. The conveying speed is selected by the staff according to the actual situation and will not be described in detail here. The adjustment time refers to the time required for the workpiece gap to reach the workpiece gap when the workpiece does not move after the priority position and the workpiece continues to move at the conveying speed before the priority position.

[0157] Step 313: Match the blocking position from a preset blocking position recognition model according to the position image.

[0158] The blocking position recognition model refers to a neural network model obtained through sample training in advance. The blocking position recognition model can recognize from the picture a blocking position suitable for blocking the workpiece after the priority position to increase the workpiece gap.

[0159] Step 314: Match the blocking stroke from a preset blocking stroke matching model according to the blocking position and the adjustment duration.

[0160] The blocking stroke matching model refers to a neural network model obtained through sample training in advance. The blocking stroke matching model can match the blocking stroke of blocking the workpiece according to the adjusted time through the suspension bridge device and then disengaging.

[0161] Step 315: Control the preset suspension bridge device according to the blocking stroke to block the workpiece after the priority position so that the workpiece after the priority position moves backward.

[0162] The workpiece after the priority position is blocked by the suspension bridge device. At this time, the workpiece after the priority position is blocked and cannot continue to move, and the workpiece before the priority position continues to move synchronously with the conveying device, thereby expanding the space gap.

[0163] Reference Figure 5 , the gap adjustment method includes the following steps:

[0164] Step 400: After the workpiece is moved backward by the suspension bridge device, a backward movement image between the workpiece position and the priority position is acquired.

[0165] The backward image refers to a picture of the workpiece between the workpiece position and the priority position. The backward image can be obtained through a camera. The method for obtaining the backward image is selected by the staff according to the actual situation and will not be elaborated here.

[0166] Step 401: judging whether the gap between the workpieces exceeds the preset workpiece gap according to the backward image from the preset workpiece gap judgment model.

[0167] The workpiece gap judgment model refers to a neural network model obtained through sample training in advance. The workpiece gap judgment model can judge from the picture whether the width of the gap between the workpieces between the workpiece position and the priority position exceeds the workpiece gap.

[0168] Step 402: When the gap between the workpieces does not exceed the preset workpiece gap, the workpiece features are identified from a preset workpiece feature recognition model according to the backward image.

[0169] The gap between the workpieces does not exceed the workpiece gap, which means that the gap between the spaces needs to be adjusted. The workpiece feature recognition model refers to a neural network model obtained through sample training in advance, and the workpiece feature recognition model can recognize workpiece features from images.

[0170] Step 403: Matching the adjustment stroke from the preset gap adjustment model based on the workpiece characteristics.

[0171] The gap adjustment model refers to a neural network model obtained in advance through sample training. The gap adjustment model can match the gap between the identified workpiece features that does not exceed the workpiece gap to the adjustment stroke of the workpiece gap.

[0172] Step 404: Controlling a preset gap adjustment device to adjust the gap between the workpieces according to the adjustment stroke.

[0173] The gap adjustment device refers to a device used to adjust the gap between workpieces. The gap adjustment device can adopt a mechanical arm. The gap adjustment device is selected by the staff according to the actual situation and will not be elaborated here.

[0174] Reference Figure 6 , the workpiece exchange method comprises the following steps:

[0175] Step 500: When there is no space for the workpiece to be placed at the priority position, the hysteresis level is matched from a preset priority algorithm according to the position image.

[0176] The absence of space for the workpiece to be placed at the priority position indicates that other workpieces exist at the priority position, and the hysteresis level is the priority number of the workpiece existing at the priority position calculated by the priority algorithm.

[0177] Step 501: When the hysteresis level falls into a preset hysteresis range, an extraction stroke is matched from a preset extraction stroke matching model according to the workpiece position and the priority position.

[0178] The hysteresis range refers to the priority range where the workpiece needs to be placed back to delay processing. The hysteresis range is selected by the staff according to the actual situation and will not be described here. The hysteresis series falling into the hysteresis range means that the workpiece at the workpiece position and the workpiece at the priority position can be exchanged at this time. The extraction stroke matching model refers to a neural network model obtained through sample training in advance. The extraction stroke matching model can match the extraction stroke that takes the workpiece at the workpiece position and the workpiece at the priority position out of the conveyor in sequence.

[0179] Step 502: Control the preset suspension bridge device according to the extraction stroke to sequentially extract the workpiece position and the workpiece at the priority position from the preset conveying device.

[0180] The workpiece at the workpiece position and the workpiece at the priority position are both extracted onto the suspension bridge device through the suspension bridge device.

[0181] Step 503: matching the exchange stroke from a preset exchange stroke matching model according to the workpiece position and the priority position.

[0182] The exchange stroke matching model refers to a neural network model obtained in advance through sample training. The exchange stroke matching model can match the exchange stroke that puts the workpiece at the workpiece position and the workpiece at the priority position back from the suspension bridge device to the conveying device and exchanges the positions.

[0183] Step 504: Control the preset suspension bridge device according to the exchange stroke to place the workpiece on the suspension bridge device in the workpiece position and the priority position in sequence, and exchange the positions of the workpiece at the workpiece position and the priority position.

[0184] The workpiece at the workpiece position and the workpiece at the priority position are exchanged by the suspension bridge device, thereby reducing the situation where the workpiece at the workpiece position is moved forward and other workpieces at and after the priority position are affected.

[0185] Reference Figure 7 , the workpiece guiding method comprises the following steps:

[0186] Step 600: Matching a guide position from a preset guide position recognition model according to the workpiece image.

[0187] The guide position recognition model refers to a neural network model obtained in advance through sample training. The guide position recognition model can recognize from the image the guide position of the point of action that is likely to partially separate the workpiece from the conveying device.

[0188] Step 601: Match a guidance stroke from a preset guidance stroke matching model according to the guidance position and the take-away stroke.

[0189] The guiding device refers to a device used to separate the workpiece from the conveying device to reduce the situation where the workpiece is close to the conveying device and the suspension bridge device cannot take the workpiece away. The guiding device can be a mechanical arm. The guiding device is selected by the staff according to the actual situation and will not be described here. The guiding stroke matching model refers to a neural network model obtained through sample training in advance. The guiding stroke matching model can correct the taking-away stroke according to the guiding position, thereby matching the guiding stroke that allows the suspension bridge device to take the workpiece away and separate the workpiece from the conveying device through the guiding device.

[0190] Step 603: Control the guiding device preset on the suspension bridge device to lift one end of the workpiece at the guiding position according to the guiding stroke to guide the workpiece into the suspension bridge device.

[0191] The workpiece is lifted by the guiding device, thereby separating the workpiece from the conveying device, thereby facilitating the bridge device to take the workpiece away.

[0192] Based on the same inventive concept, an embodiment of the present invention provides a flexible open factory scheduling system, including:

[0193] An acquisition module 700 is used to acquire a workpiece image, a position image and a backward movement image;

[0194] A memory 701, used for storing a program of a control method of any one of the flexible open factory scheduling methods;

[0195] Processor 702, the program in the memory can be loaded and executed by the processor and realize any one of the control methods of a flexible open factory scheduling method

[0196] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0197] An embodiment of the present invention provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed by a flexible open factory scheduling method.

[0198] Computer storage media include, for example, various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0199] Based on the same inventive concept, an embodiment of the present invention provides an intelligent terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute a flexible open factory scheduling method.

[0200] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0201] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A flexible open factory scheduling method, characterized in that: include: acquiring a workpiece image of the workpiece; Matching the processing time from a preset processing time matching model according to the workpiece image; Calculate the quotient of processing time and preset completion time and define it as time utilization rate; When the time utilization is greater than the preset workshop utilization, a redistribution step is matched from a preset workpiece redistribution model according to the processing time; Controlling a preset carrier to redistribute the workpieces into the workshop according to the redistribution steps; When the time utilization is not greater than the preset workshop utilization, the workshop number is matched from the preset workshop number matching model according to the time utilization; According to the workshop number, the preset carrier is controlled to transport the workpiece to the workshop for processing.

2. A flexible open factory scheduling method according to claim 1, characterized in that: The invention also includes a machine position scheduling method, wherein the machine position scheduling method includes: Calculate the quotient of the processing time and the preset operating time and define it as the machine utilization rate; When the machine utilization rate is greater than the preset operation utilization rate, the processing time is defined as the operation time; Based on the situation that the machine position utilization rate is not greater than the preset operation utilization rate, the processing process and the process duration corresponding to the processing process are matched from the preset process recognition model according to the workpiece image; Matching the process allocation plan from the preset process matching model according to the running time, processing process and process duration; According to the process allocation plan, the preset processing device is controlled to process the workpiece, and the process allocation plan is displayed through a preset plan display method.

3. A flexible open factory scheduling method according to claim 1, characterized in that: Also included is a workpiece scheduling method, the workpiece scheduling method comprising: Matching a priority number from a preset priority algorithm according to the workpiece image; When the priority number falls within a preset priority range, the workpiece position is matched from a preset workpiece position recognition model according to the workpiece image; Matching the take-off stroke from a preset take-off stroke matching model according to the position of the workpiece; Controlling the preset suspension bridge device according to the take-off stroke to transport the workpiece onto the suspension bridge and take it away from the preset conveying device; Matching a priority position from a preset priority position matching model according to the priority number; Matching a placement trip from a preset placement trip matching model according to the priority position; The preset suspension bridge device is controlled according to the placement stroke to transport the workpiece to the preferred position.

4. A flexible open factory scheduling method according to claim 3, characterized in that: The workpiece scheduling method further includes: When the priority number falls within a preset priority range, obtaining a position image of the priority position; Judging whether there is space for placing the workpiece at the priority position from a preset workpiece position judgment model according to the workpiece image and the position image; When there is no space for the workpiece to be placed in the priority position, the length of the workpiece is identified from a preset workpiece length identification model according to the workpiece image; identifying the workpiece gap from a preset workpiece gap recognition model according to the position image; Matching the adjustment length from a preset adjustment length recognition model according to the workpiece length and the workpiece gap; Calculating the quotient of the adjustment length and the preset conveying speed of the conveying device and defining the quotient as the adjustment time length; Matching the blocking position from a preset blocking position recognition model according to the position image; Matching a blocking stroke from a preset blocking stroke matching model according to the blocking position and the adjustment duration; The preset suspension bridge device is controlled according to the blocking stroke to block the workpiece after the priority position so that the workpiece after the priority position moves backward.

5. A flexible open factory scheduling method according to claim 4, characterized in that: The workpiece scheduling method further includes a gap adjustment method, and the gap adjustment method includes: After the workpiece is moved backward by the suspension bridge device, a backward moving image between the workpiece position and the priority position is acquired; judging whether the gap between the workpieces exceeds the preset workpiece gap from a preset workpiece gap judging model according to the backward-moved image; When the gap between the workpieces does not exceed a preset workpiece gap, identifying workpiece features from a preset workpiece feature recognition model according to the backward-shifted image; Matching the adjustment stroke from a preset gap adjustment model based on the workpiece characteristics; The preset gap adjustment device is controlled according to the adjustment stroke to adjust the gap between the workpieces.

6. A flexible open factory scheduling method according to claim 5, characterized in that: The workpiece scheduling method further includes a workpiece exchange method, and the workpiece exchange method includes: When there is no space for the workpiece to be placed in the priority position, the hysteresis series is matched from the preset priority algorithm according to the position image; When the hysteresis series falls into a preset hysteresis range, an extraction stroke is matched from a preset extraction stroke matching model according to the workpiece position and the priority position; According to the extraction stroke, the preset suspension bridge device is controlled to sequentially extract the workpieces at the workpiece position and the priority position from the preset conveying device; Matching the exchange stroke from a preset exchange stroke matching model according to the workpiece position and the priority position; The preset suspension bridge device is controlled according to the exchange stroke to place the workpiece on the suspension bridge device in the workpiece position and the priority position in sequence, and the positions of the workpiece at the workpiece position and the priority position are exchanged.

7. A flexible open factory scheduling method according to claim 3, characterized in that: The workpiece scheduling method further includes a workpiece guiding method, and the workpiece guiding method includes: matching the guide position from a preset guide position recognition model according to the workpiece image; Matching a guide stroke from a preset guide stroke matching model according to the guide position and the take-away stroke; According to the guide stroke, the guide device preset on the suspension bridge device is controlled to lift one end of the workpiece at the guide position to guide the workpiece into the suspension bridge device.

8. A flexible open factory scheduling system, characterized in that: include: An acquisition module, used for acquiring a workpiece image, a position image and a backward movement image; A memory for storing a program of a control method of a flexible open factory scheduling method according to any one of claims 1 to 7; The program in the memory can be loaded and executed by the processor to implement a control method of a flexible open factory scheduling method as claimed in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: The device stores a computer program which can be loaded by a processor and executes the flexible open factory scheduling method according to any one of claims 1 to 7.

10. An intelligent terminal, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes any one of the flexible open factory scheduling methods according to claims 1 to 7.

Images