Factory simulation method and device
By abstracting the production factors of the factory production line into neuron-like and simulated based on the feedback stimulation chain, the problem that traditional assembly lines cannot meet the production needs of complex battery products is solved, and efficient optimization design and economic benefits of the factory production line are achieved.
Patent Information
- Application Number
- CN202210020382.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-01-07
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2042-01-07
AI Technical Summary
The traditional fixed assembly line form cannot meet the process requirements in the production process of complex battery products, resulting in low efficiency and high cost problems.
By abstracting the production factors of the factory production line into neuron-like and simulated based on the feedback stimulation chain between the neurons, the real production process of the factory is simulated to optimize the factory production line design.
It realizes efficient and optimized design of factory production lines, reduces simulation costs, improves production efficiency, and obtains economic benefits.
Smart Images

Figure CN114358622B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of simulation technology, and in particular to a factory simulation method and device. Background Art
[0002] As battery products become more complex, their processes become more complicated. The fixed traditional assembly line format can no longer meet the needs of the battery product production process. It is necessary to optimize the layout, process, logistics, etc. of the factory production line to avoid problems such as low efficiency and high cost. Summary of the invention
[0003] An object of the present invention is to provide a factory simulation method to facilitate optimization of factory production line design.
[0004] To achieve the above object, the present invention provides a factory simulation method, which includes:
[0005] Acquire multiple production factors running in a working area of a factory production line, and determine multiple neuron-like factors and attribute parameters of each neuron-like factor for factory simulation according to the multiple production factors;
[0006] At preset time intervals, the following operations are performed cyclically to determine the attribute parameters of each neuron-like class at each moment in the factory simulation period:
[0007] Determine, according to the attribute parameters of each neuron-like at the current moment, a feedback stimulation chain formed between multiple neuron-like at the current moment, and determine, according to the feedback stimulation chain, the attribute parameters of each neuron-like at the next moment; wherein the next moment is separated from the current moment by the preset time interval;
[0008] The factory simulation result is determined according to the attribute parameters of each neuron-like object at each moment in the factory simulation period.
[0009] In an embodiment of the present invention, by acquiring multiple production factors running in the working area of the factory production line, multiple class neurons and attribute parameters of each class neuron for factory simulation are determined according to the multiple production factors; according to the preset time interval, the following operations are performed cyclically to determine the attribute parameters of each class neuron at each moment in the factory simulation period: according to the attribute parameters of each class neuron at the current moment, the feedback stimulation chain formed between the multiple class neurons at the current moment is determined, and the attribute parameters of each class neuron at the next moment are determined according to the feedback stimulation chain; wherein the next moment is separated from the current moment by the above preset time interval; according to the attribute parameters of each class neuron at each moment in the factory simulation period, the factory simulation result is determined. By abstracting the production factors of the factory production line into class neurons, the operation of the factory production line is simulated based on the feedback stimulation chain between class neurons to simulate the real production of the factory, thereby facilitating the optimization of the factory production line design.
[0010] Another object of the present invention is to provide a factory simulation device that can conveniently optimize the design of factory production lines.
[0011] To achieve the above object, the present invention provides a plant simulation device, which includes:
[0012] A neuron-like determination module, used to obtain a plurality of production factors running in a working area of a factory production line, and determine a plurality of neuron-like components and attribute parameters of each neuron-like component for factory simulation according to the plurality of production factors;
[0013] The feedback stimulation simulation module is used to perform the following operations cyclically at preset time intervals to determine the attribute parameters of each neuron-like object at each moment in the factory simulation period:
[0014] Determine, according to the attribute parameters of each neuron-like at the current moment, a feedback stimulation chain formed between multiple neuron-like at the current moment, and determine, according to the feedback stimulation chain, the attribute parameters of each neuron-like at the next moment; wherein the next moment is separated from the current moment by the preset time interval;
[0015] The simulation result determination module is used to determine the factory simulation result according to the attribute parameters of each neuron-like object at each moment in the factory simulation period.
[0016] In the embodiment of the present invention, by setting a class neuron determination module, multiple production factors running in the working area of the factory production line are obtained, and multiple class neurons and attribute parameters of each class neuron used for factory simulation are determined according to the multiple production factors; by setting a feedback stimulation simulation module, the following operations are performed cyclically according to the preset time interval to determine the attribute parameters of each class neuron at each moment in the factory simulation period: according to the attribute parameters of each class neuron at the current moment, the feedback stimulation chain formed between the multiple class neurons at the current moment is determined, and the attribute parameters of each class neuron at the next moment are determined according to the feedback stimulation chain; wherein the next moment is separated from the current moment by the above preset time interval; by setting a simulation result determination module, the factory simulation result is determined according to the attribute parameters of each class neuron at each moment in the factory simulation period. By abstracting the production factors of the factory production line into class neurons, the operation of the factory production line is simulated based on the feedback stimulation chain between class neurons to simulate the real production of the factory, thereby facilitating the optimization of the factory production line design.
[0017] Another object of the present invention is to provide a computer device that can conveniently optimize the design of factory production lines.
[0018] To achieve the above objectives, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above factory simulation method when executing the computer program.
[0019] From the above description, it can be seen that the computer device provided by the embodiment of the present invention obtains multiple production factors running in the working area of the factory production line, and determines multiple class neurons and attribute parameters of each class neuron for factory simulation according to the multiple production factors; according to the preset time interval, the following operations are performed cyclically to determine the attribute parameters of each class neuron at each moment in the factory simulation period: according to the attribute parameters of each class neuron at the current moment, the feedback stimulation chain formed between the multiple class neurons at the current moment is determined, and the attribute parameters of each class neuron at the next moment are determined according to the feedback stimulation chain; wherein the next moment is separated from the current moment by the above preset time interval; according to the attribute parameters of each class neuron at each moment in the factory simulation period, the factory simulation result is determined. By abstracting the production factors of the factory production line into class neurons, the operation of the factory production line is simulated based on the feedback stimulation chain between class neurons to simulate the real production of the factory, thereby facilitating the optimization of the factory production line design.
[0020] Another object of the present invention is to provide a computer-readable storage medium that can facilitate optimization of factory production line design.
[0021] To achieve the above objective, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for executing the above plant simulation method.
[0022] The computer-readable storage medium provided by the embodiment of the present invention obtains multiple production factors running in the working area of the factory production line, and determines multiple class neurons and attribute parameters of each class neuron for factory simulation according to the multiple production factors; according to the preset time interval, the following operations are performed cyclically to determine the attribute parameters of each class neuron at each moment in the factory simulation period: according to the attribute parameters of each class neuron at the current moment, the feedback stimulation chain formed between the multiple class neurons at the current moment is determined, and the attribute parameters of each class neuron at the next moment are determined according to the feedback stimulation chain; wherein the next moment is separated from the current moment by the above preset time interval; according to the attribute parameters of each class neuron at each moment in the factory simulation period, the factory simulation result is determined. By abstracting the production factors of the factory production line into class neurons, the operation of the factory production line is simulated based on the feedback stimulation chain between the class neurons to simulate the real production of the factory, thereby facilitating the optimization of the factory production line design. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] The following drawings are intended only to illustrate and explain the present invention, and are not intended to limit the scope of the present invention.
[0024] Figure 1 is a schematic diagram of the implementation process of the factory simulation method according to an embodiment of the present invention;
[0025] Figure 2 is a schematic diagram of a specific implementation process of step 101 in a specific embodiment of the present invention;
[0026] Figure 3 is a schematic diagram of a neuron-like model according to a specific embodiment of the present invention;
[0027] Figure 4 It is a schematic diagram of a stimulation feedback process formed by a neuron-like structure in a specific example of the present invention;
[0028] Figure 5 Schematic diagram of the secondary stimulation feedback process formed by a neuron-like structure in a specific example of the present invention;
[0029] Figure 6 is a schematic diagram of a specific implementation process of step 102 in a specific example of the present invention;
[0030] Figure 7 is a schematic diagram of another specific implementation process of step 102 in a specific example of the present invention;
[0031] Figure 8It is a schematic diagram of the implementation process of the factory simulation method in a specific embodiment of the present invention;
[0032] Fig. 9 is a schematic diagram of attribute parameters of a class neuron in a specific example of the present invention;
[0033] Fig.10 is a schematic diagram of specific attribute parameters of six neuron classes in a specific example of the present invention;
[0034] Fig.11 It is a schematic diagram of a cost curve obtained by a simulation in a specific example of the present invention;
[0035] Fig.12 It is a schematic diagram of a profit curve obtained by a simulation in a specific example of the present invention;
[0036] Fig.13 is a structural schematic diagram of a factory simulation device according to an embodiment of the present invention;
[0037] Fig.14 is a structural schematic diagram of a factory simulation device according to a specific embodiment of the present invention;
[0038] Fig.15 It is a structural schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION
[0039] The present application is further described in detail below through the accompanying drawings and examples. Through these descriptions, the characteristics and advantages of the present application will become clearer and more specific. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0040] The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. Although various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise noted.
[0041] In addition, the technical features involved in different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.
[0042] In order to optimize the design of factory production lines, the present invention provides a factory simulation method. Figure 1 As shown, including:
[0043] Step 101: Acquire multiple production factors running in the working area of the factory production line, and determine multiple class neurons and attribute parameters of each class neuron for factory simulation according to the multiple production factors;
[0044] Step 102: According to the preset time interval, the following operations are performed cyclically to determine the attribute parameters of each neuron-like object at each moment in the factory simulation period:
[0045] Determine the feedback stimulation chain formed between multiple neuron-like neurons at the current moment according to the attribute parameters of each neuron-like neuron at the current moment, and determine the attribute parameters of each neuron-like neuron at the next moment according to the feedback stimulation chain; wherein the next moment is separated from the current moment by the above-mentioned preset time interval;
[0046] Step 103: Determine the factory simulation result according to the attribute parameters of each neuron-like object at each moment in the factory simulation period.
[0047] As can be seen from the above, by obtaining multiple production factors running in the working area of the factory production line, multiple class neurons and attribute parameters of each class neuron for factory simulation are determined according to the multiple production factors; according to the preset time interval, the following operations are performed cyclically to determine the attribute parameters of each class neuron at each moment in the factory simulation period: according to the attribute parameters of each class neuron at the current moment, the feedback stimulation chain formed between multiple class neurons at the current moment is determined, and the attribute parameters of each class neuron at the next moment are determined according to the feedback stimulation chain; wherein the next moment is separated from the current moment by the above preset time interval; according to the attribute parameters of each class neuron at each moment in the factory simulation period, the factory simulation result is determined. By abstracting the production factors of the factory production line into class neurons, the operation of the factory production line is simulated based on the feedback stimulation chain between class neurons to simulate the real production of the factory, so as to facilitate the optimization of the factory production line design.
[0048] In an embodiment of the present invention, the inventors found that when using a factory production line to produce lithium batteries, there are mutual connections between different production factors. For example, when feeding raw materials, employees need to carry raw material barrels to the raw material placement area to carry raw materials to the production machine. As long as there is material in the raw material area, the raw material barrel is empty, and the production machine needs to feed, employees can feed raw materials according to this process flow, that is, there is a mutual connection between the production factors of the raw material placement area, employees, raw material barrels, and production machines. At the same time, once the state of one or several production factors changes, this connection may no longer exist. For example, if there is no raw material in the raw material area, the employee will no longer perform the feeding operation. These characteristics are very similar to the stimulation feedback characteristics of neurons, so the inventors abstracted the production factors of the factory production line into neuron-like neurons, and based on the stimulation feedback characteristics of neurons, designed a neuron-like model of the stimulation feedback mechanism to simulate the production process of the factory production line.
[0049] In the specific implementation process, first obtain multiple production factors running in the working area of the factory production line, and determine multiple class neurons and attribute parameters of each class neuron for factory simulation according to the multiple production factors. In a specific embodiment, the above-mentioned production factors mainly refer to all factors and environmental conditions necessary for the material production of the factory production line, including human factors, material factors and their combined factors. And the multiple production factors are at least two production factors. In this specific embodiment, the multiple production factors running in the working area of the factory production line include: production machines (such as mixers, coating machines, etc.), instruments, robotic arms, production robots, various functional areas (such as raw material areas, product areas, etc.) and employees, etc. Those skilled in the art can understand that the above is only an example, and the present invention is not limited here. In the specific implementation, since the factory simulation is generally performed before the factory production line is put into production, in the specific embodiment, the multiple production factors running in the working area of the factory production line are obtained from the design layout data of the factory. Specifically, the above-mentioned production factors can be obtained from the CAD (Computer Aided Design, Computer Aided Design) drawings of the factory production line, including the type of the production factor, the process involved in the production line, the scope of activities and other information.
[0050] In a specific embodiment, based on multiple production factors, multiple class neurons and attribute parameters of each class neuron for factory simulation are determined, including: grouping multiple production factors according to type, abstracting multiple production factors into multiple class neurons according to the grouping situation, and determining the attribute parameters of each class neuron. Figure 2 As shown, including:
[0051] Step 201: Determine the classification type of the neuron-like class according to the grouping situation;
[0052] Step 202: According to the classification type, the class neurons corresponding to each production factor are grouped and numbered to obtain a set consisting of multiple class neurons.
[0053] When a specific factory production line is in production, there will inevitably be multiple production factors of the same type. When the production factors are abstracted into class neurons, they can be grouped according to the type of production factors and abstracted into class neurons, and the class neurons are numbered according to the grouping. Therefore, the production factors represented by each class neuron can be directly known through the numbering, which is convenient for human-computer interaction during simulation calculations. For example, if multiple production factors include 3 employees, 1 functional area, and 4 production machines, they can be abstracted into class neurons numbered A1, B1, B2, B3, C1, C2, C3, and C4, respectively, where the letters in the number represent the type of production factors represented (A represents the functional area, B represents the employee, and C represents the production machine), and the last digit represents the serial number of the class neuron in the same type. The set N composed of class neurons A1, class neurons B1, class neurons B2, class neurons B3, class neurons C1, class neurons C2, class neurons C3, and class neurons C4 is the class neuron set used for subsequent simulation.
[0054] In a specific embodiment of the present invention, a neuron-like is an abstract model that has the characteristics of receiving stimulation and responding to stimulation. Two or more neuron-likes can form a stimulation feedback mechanism. For example, when neuron-like A is in a certain state, a stimulus is triggered, and neuron-like A specifies neuron-like B to do something. Neuron-like B receives this stimulus, forms a stimulus feedback chain, and switches its own state to the state of doing the thing. When neuron-like B completes the task, it gives feedback to neuron-like A, and the two switch states together, and the stimulus feedback chain is eliminated. Figure 3 , which is a schematic diagram of a neuron-like model constructed in this specific embodiment, including: a part 301 that carries its own state information, a stimulation emission area 302 and a feedback emission area 303.
[0055] In addition, when the production factors are abstracted into class neurons, the attribute parameters of each class neuron are determined together according to the relevant information of the production factors, specifically including: one or any combination of stimulation area occupancy parameters, feedback area occupancy parameters, production status parameters, cost parameters and profit parameters. The stimulation area occupancy parameters are used to indicate the next level class neurons to be stimulated by this class of neurons; the feedback area occupancy parameters are used to indicate which class of neurons of the previous level this class of neurons is stimulated by, that is, which class of neurons the results are to be fed back to; the production status parameters are mainly used to characterize the relevant status of this class of neurons in the production process, for example, including: working status, loading status, running time, fault conditions, movement direction and trajectory, etc., mainly according to the specific settings of the factory production line to be simulated, and the present invention is not limited here. The cost parameters and profit parameters are mainly used to characterize the current cost required by this class of neurons and the profits that can be brought.
[0056] In order to better illustrate the embodiments of the present invention, based on Figure 4 The first-order stimulus feedback process shown and Figure 5 The secondary stimulus feedback process shown in the figure specifically illustrates the working mechanism of neuron-like structures and the formation and elimination of stimulus feedback chains.
[0057] Figure 4 In the figure, neuron A is indicated by the background color shown in the figure, and neuron B is indicated by the slash. At time t0, A is in state 0 and B is in state 0; at time t1, A and B meet the stimulus feedback formation conditions, and the stimulus emission area can be marked with B's number (fill in the slash), and B is marked with A's number in the feedback emission area, and the background color is filled in, and A and B are transformed into state 1; at time t2, B has completed the work and met the stimulus feedback termination conditions, A is transformed into state 3, no longer stimulating, and the stimulus generation area is cleared; B is transformed into state 3, feedback is completed, and the feedback emission area is cleared. It is particularly important to note that state 3 can be the same as state 1 or different from state 1.
[0058] Figure 5 In the figure, add a class neuron C and fill it with dots. At time t0, A is in state 0, B is in state 0, and C is in state 0. At time t1, A and B meet the stimulus feedback formation conditions, and the stimulus emission area is marked with B's number (filled with slashes), B is marked with A's number in the feedback emission area, and fills in the background color. A and B change to state 1. At this time, B and C meet the stimulus feedback formation conditions, and B's stimulus emission area is marked with C's number (filled with dots), C is marked with B's number in the feedback emission area, and fills in slashes. At this time, the A-B-C secondary stimulus feedback chain is formed. At time t2, C has completed the work and meets the stimulus feedback termination conditions. C changes to state 3. According to the number in C's feedback area, B can be found, and according to the number in B's feedback area, A can be found. A, B and C all change to state 3, and the A-B-C secondary stimulus feedback chain is destroyed, and the stimulus feedback areas of A, B and C are cleared.
[0059] By analogy, an N-level stimulus feedback chain can be constructed by gradually increasing the first-level stimulus feedback, the second-level stimulus feedback, and the third-level stimulus feedback. When the N-level stimulus feedback chain meets the termination condition, the entire stimulus feedback chain is destroyed and re-formed into an N-1-level stimulus feedback chain, which gradually decreases and finally forms a first-level stimulus feedback to complete the work.
[0060] Based on the stimulus feedback connection formation and elimination process described above, the simulation operation of the factory production line can be realized. Specifically, the following operations are performed cyclically at preset time intervals to determine the attribute parameters of each neuron-like at each moment in the factory simulation period:
[0061] According to the attribute parameters of each neuron-like at the current moment, the feedback stimulation chain formed between multiple neuron-like at the current moment is determined, and the attribute parameters of each neuron-like at the next moment are determined according to the feedback stimulation chain; wherein the next moment is separated from the current moment by the above-mentioned preset time interval.
[0062] In a specific embodiment, a time period is set as a factory simulation period, and a time step is preset as a preset time interval. For example, the simulation period is 1 hour, and 5 minutes is taken as the preset time interval. The attribute parameters of each neuron-like object at that moment are determined every 5 minutes, thereby obtaining the attribute parameters of each neuron-like object at 12 moments within 1 hour.
[0063] Specifically, according to the attribute parameters of each neuron-like neuron at the current moment, the feedback stimulation chain formed between multiple neuron-like neurons at the current moment is determined, such as Figure 6 As shown, including:
[0064] Step 601: traverse a set consisting of multiple class neurons, determine the feedback stimulation chain that is currently working according to the stimulation area occupancy parameter, feedback area occupancy parameter and production state parameter of each class neuron in the set at the current moment, and obtain a working subset consisting of class neurons included in the working feedback stimulation chain, and a non-working subset;
[0065] Step 602: traverse the non-working subset, and according to the stimulation area occupancy parameter, feedback area occupancy parameter and production state parameter of each class neuron in the non-working subset, as well as the preset stimulation feedback formation condition parameter, obtain the newly constructed feedback stimulation chain at the current moment, and update the working subset and the non-working subset;
[0066] Step 603: traverse the updated working subset, and determine the feedback stimulation chain that terminates the work at the current moment according to the stimulation area occupancy parameter, feedback area occupancy parameter and production state parameter of each class neuron in the updated working subset, as well as the preset stimulation feedback termination condition parameter;
[0067] Step 604: Determine the feedback stimulation chain formed between multiple neuron-like chains at the current moment according to the feedback stimulation chain currently in operation, the newly constructed feedback stimulation chain at the current moment, and the feedback stimulation chain terminated at the current moment.
[0068] Among them, the specific implementation process of step 601 is to take out the class neurons included in the working feedback stimulation chain from the set composed of multiple class neurons to form a working subset, and the remaining class neurons constitute a non-working subset.
[0069] In a specific embodiment, when step 602 is implemented, the stimulus feedback formation condition parameters are preset in advance, which are based on the conditions under which different types of neurons can form a stimulus feedback chain when the actual production line is produced. For example, for the class neurons representing the rest area and the class neurons representing the employees, the following conditions are satisfied: the production status parameter of the class neurons representing the rest area is displayed as being in an empty state; the production status parameter of the class neurons representing the employees is displayed as being in an empty state, and the employee item column is empty; the stimulus zone occupancy parameter of the class neurons representing the rest area is empty; the feedback zone occupancy parameter of the class neurons representing the employees is empty. If this condition is met, it is determined that a stimulus feedback chain is formed between the class neurons representing the rest area and the class neurons representing the employees. If there is a newly constructed feedback stimulus chain at the current moment, and at least two class neurons in the non-working subset are in a working state, then these class neurons in a working state are added to the working subset, and these class neurons are deleted in the non-working subset to update the working subset and the non-working subset.
[0070] When step 603 is implemented, it is similar to step 602, except that when step 603 is implemented, it is based on the preset stimulus feedback termination condition parameter, which represents the conditions under which different types of neurons forming the stimulus feedback chain will stop working, and the stimulus feedback chain that has been formed is eliminated. For example, for the stimulus feedback chain formed between the above-mentioned class neurons representing the rest area and the class neurons representing the employees, if the stimulus zone occupancy parameter of the class neurons representing the rest area is the employee class neuron number; the feedback zone occupancy parameter of the class neurons representing the employees is the rest area class neuron number; the production status parameter of the class neurons representing the employees shows that the employee's physical strength value is full, then the employee's rest in the rest area is completed, and the above-mentioned stimulus feedback chain is eliminated.
[0071] By arranging the feedback stimulation chains currently in operation, the newly constructed feedback stimulation chains and the terminated feedback stimulation chains determined in step 601, step 602 and step 603, all the feedback stimulation chains at the current moment and the corresponding working states can be obtained.
[0072] After obtaining the feedback stimulus chain formed between multiple neuron-like neurons at the current moment, the attribute parameters of each neuron-like neuron at the next moment are determined according to the feedback stimulus chain. Figure 7 As shown, including:
[0073] Step 701: determining a mapping relationship between the attribute parameters of each neuron-like object at the next moment and the attribute parameters of each neuron-like object at the current moment according to a feedback stimulation chain formed between multiple neuron-like objects at the current moment;
[0074] Step 702: Determine the attribute parameters of each neuron-like object at the next moment according to the above mapping relationship and the attribute parameters of each neuron-like object at the current moment.
[0075] Since the feedback stimulation chain can reflect whether the neuron-like state is working and how it is working, the state of each neuron-like state at the next moment can be predicted based on the feedback stimulation chain at the current moment, and the mapping relationship of the change of each neuron-like state can be obtained, and the attribute parameters of each neuron-like state at the current moment are used as independent variables. The dependent variable, that is, the attribute parameters of each neuron-like state at the next moment, can be obtained by combining the mapping relationship and the independent variable. After a preset time interval, the attribute parameters obtained in the previous operation are used as the attribute parameters of each neuron-like state at the current moment in this operation, thereby realizing the operation of the factory.
[0076] The preset time interval is preset in advance and can be 1 second, 2 seconds, 1 minute, etc. It is set according to actual needs and is not limited here. In a specific embodiment, the cycle termination condition is generally that the cycle time reaches the factory simulation period, but it can also be determined when to terminate according to the factory simulation results. For example, if the simulation achieves the expected benefit target from the factory simulation results, the simulation can be stopped directly, so the specific cycle termination condition is not limited here.
[0077] In a specific embodiment, in order to simplify the calculation, when determining the mapping relationship, it can be determined separately by the response state of the class neuron. The response state of the class neuron is divided into a self-response state and an other-response state, wherein the self-response state means that the class neuron in this state does not need to consider the state of other class neurons, for example, the blender is stirring, that is, the blender is in a self-response state, and there are still 10 minutes before the stirring is completed. Its processing at this moment is that the time hourglass minus 1 equals 9; the other-response state means that the state of other class neurons needs to be considered, and they are in a coordinated working relationship, so joint processing is required, and the class neuron in the working state is not in a self-response state but in an other-response state.
[0078] For the updated working subset, the response states of the neuron-like are distinguished to obtain the self-response state sub-subset and the other-response state sub-subset of the working subset. For the neuron-like in the self-response state sub-subset, the mapping relationship with the next moment can be determined based on the attribute parameters of the production state of the neuron-like at the current moment. For the neuron-like in the other-response state sub-subset, it is necessary to combine the feedback stimulation chain formed by the neuron-like to determine, specifically, to combine the neuron-like and other neuron-like recorded in the feedback area of the neuron-like to jointly determine the mapping relationship. It can be seen that by distinguishing the response states of the neuron-like, the self-response state does not require complex calculations compared to the other-response state, which can further reduce the amount of simulation calculations and improve simulation efficiency.
[0079] After the cycle is completed, the attribute parameters of each class neuron at each moment in the factory simulation period are obtained, and the factory simulation results are determined according to the attribute parameters of each class neuron at each moment in the factory simulation period. In the specific implementation, it includes: according to the cost parameters and profit parameters of each class neuron at each moment in the factory simulation period, the simulation cost data and simulation profit data of the factory operation corresponding to the factory simulation period are determined to obtain the factory simulation results. The formation, operation and elimination of the stimulus feedback chain represent the process in which the production factors represented by the class neuron participate in the factory production line. In this process, consumption and output will inevitably occur. Therefore, when the attribute parameters of each class neuron at each moment are determined according to the feedback stimulus chain, the cost parameters and profit parameters can be determined, and the cost parameters and profit parameters of each class neuron at each moment in the factory simulation period are analyzed and counted to obtain the factory simulation results, including the simulation cost data and simulation profit data of the factory operation corresponding to the factory simulation period, which can be used for the subsequent design, commissioning and maintenance of the factory production line.
[0080] In a specific embodiment of the present invention, in order to facilitate the description of the state parameters of the neuron-like class, such as the movement direction and trajectory, a coordinate system is introduced in the simulation. The specific implementation method is as follows: Figure 8 As shown, in Figure 1 On the basis of
[0081] Step 801: Acquire the working area data of the factory production line;
[0082] Step 802: According to the working area data, the working area is gridded to obtain a grid division for factory simulation; the grid division is divided into regions to obtain a movable region and an immovable region;
[0083] Step 803: Determine the attribute parameters of each neuron-like object according to the grid divisions, movable areas, and immovable areas.
[0084] Specifically, the working area data is obtained from the CAD of the factory production line, and it is gridded as the coordinate system for simulation. For example, the position of the class neuron is represented by the grid of the i-th row and j-th column, and the coordinates of the class neuron are represented by (i, j). This facilitates the calculation of parameters and further reduces the amount of simulation calculations. In addition, in order to more intuitively show how the production line works during simulation, the CAD diagram of the factory production line at each moment can be depicted according to the attribute parameters of the class neuron at each moment, and in order to facilitate human-computer interaction, different icons can be designed for different types of class neurons.
[0085] The factory simulation method provided in the specific embodiment of the present invention not only facilitates the optimization of the factory production line design, but also abstracts the production elements of the factory production line into neuron-like elements and simulates the factory production line with a feedback stimulation chain between neuron-like elements. Compared with the method of completely constructing a mirror model of the factory production line and then generating a virtual production line based on the mirror model, only the key factors affecting production are considered, and there is no need to completely mirror and copy the real factory, which greatly reduces the simulation workload and thus can greatly reduce the simulation cost.
[0086] The embodiment of the present invention also provides a specific example to specifically illustrate the factory simulation method provided by the embodiment of the present invention. This specific example is illustrated by taking the slurry production line in the lithium-ion battery production process as an example.
[0087] First, obtain the CAD drawings of the entire production line of the lithium battery factory, remove the areas unrelated to the slurry production line, extract the working area of the slurry production line and the production elements running in the working area from the drawings, including: mixer, employees, raw material placement area, empty barrel placement area, storage area, and rest area, and abstract them into class neurons. Divide the working area into a grid, determine the movable area and the immovable area, and use the row and column numbers of the grid to represent the coordinates of the class neuron. The position of the class neuron is represented by the grid of the i-th row and j-th column, and the coordinates of the class neuron are represented by (i, j). Set icons for each type of class neuron respectively, and give the initial position of each class neuron. Generally, its initial position is set to the operating position of the machine or functional area during normal production.
[0088] Among them, the attribute parameters of the neuron class in this specific example are as follows Fig. 9As shown, including: type, legend number, coordinates, whether the stimulation area is occupied, whether the feedback area is occupied, production status, loading capacity, operating time hourglass, failure rate, failure resolution time, movement trajectory, movement direction, fixed cost, non-fixed cost, profit, etc. Among them, legend number 1 represents a mixer, legend number 2 represents an employee, legend number 3 represents a raw material area, legend number 4 represents an empty barrel area, legend number 5 represents a storage area, and legend number 6 represents a rest area; whether the stimulation area is occupied and whether the feedback area is occupied, 0 is used to indicate no occupancy, and other numbers represent the class neurons represented by the corresponding legend numbers. Production status: 0 means vacant, 1 means working, 2 means handling, 4 means waiting for discharge, 6 means preparation, and 7 means rest. The specific attribute parameters of each class neuron can be adjusted according to actual production, as shown below. Fig.10 As shown, the attribute parameters of each class neuron at a certain moment. In particular, the attribute parameters of the employee type class neuron also include: inventory (0 means no occupancy, 1 means an empty barrel, 2 means a barrel for raw materials, and 3 means a barrel for products) and chain (0 means destructible, 1 means indestructible).
[0089] The simulation period t is set to 300, the time axis Δt is set to 1, and the time axis Δt is used as the interval to display a frame of the simulated CAD picture every Δt. The simulated time t' after each simulation increases by Δt until t' is greater than or equal to t, and the loop ends.
[0090] In each cycle (for the sake of ease of expression, the following uses the production factors represented by class neurons to briefly represent the corresponding class neurons. For example, "class neurons representing employees" are abbreviated as "employees"): traverse the set of 6 class neurons, determine the class neurons that are in a working state, and thus determine the working subset and the non-working subset. For the non-working subset, traverse the non-working subset, form a table based on the stimulus feedback shown in Table 1, determine whether the stimulus feedback construction conditions shown in Table 1 are met, and construct a new stimulus feedback chain.
[0091] Table 1 Stimulus feedback formation table
[0092] Neuron-like Blender staff Raw material area Empty barrel area Storage area Living Area Blender N / A a b c N / A N / A staff a N / A d f g h Raw material area b d N / A e N / A N / A Empty barrel area c f e N / A N / A N / A Storage area N / A g N / A N / A N / A N / A Living Area N / A h N / A N / A N / A N / A
[0093] In the table, N / A indicates that there is no construction condition for this situation.
[0094] The construction conditions ah are:
[0095] a(Mixer - Employee):
[0096] a1: The blender is empty; the blender stimulation area is not occupied; the employee feedback area is not occupied; the employee inventory is a bucket of raw materials; or
[0097] a2: The mixer is in an empty state; the mixer stimulation area is not occupied; the employee feedback area is not occupied; the employee inventory is a bucket of raw materials; the mixer operation position and the employee position overlap; or
[0098] a3: The blender is in the waiting state; the blender stimulation area is not occupied; the employee feedback area is not occupied; the employee inventory is empty; or
[0099] a4: The blender is in the state of waiting for shipment; the blender stimulation area is not occupied; the employee feedback area is not occupied; the employee inventory is an empty bucket; the blender operation position and the employee's position coincide.
[0100] b(Mixer-Raw Material Area):
[0101] The blender is in an empty state; the blender stimulation area is not occupied; the raw material area feedback area is not occupied; the raw material area inventory contains raw materials.
[0102] c (Mixer-empty barrel area):
[0103] The blender is in the state of waiting for shipment; the blender stimulation area is not occupied; the empty barrel area feedback area is not occupied; the empty barrel area inventory is an empty barrel.
[0104] d(Raw material area - employees):
[0105] d1: The raw material area is vacant; the raw material area stimulation area is not occupied; the employee feedback area is not occupied; the employee inventory is empty; or
[0106] d2: The raw material area is vacant; the raw material area stimulation area is not occupied; the employee feedback area is not occupied; the employee inventory is an empty bucket; the mixer operation position coincides with the employee's position.
[0107] e (Raw material area - empty barrel area):
[0108] The raw material area is vacant; the stimulation area of the raw material area is not occupied; the feedback area of the empty barrel area is not occupied; the inventory of the empty barrel area is an empty barrel.
[0109] f(Empty barrel area—employees):
[0110] f1: The empty barrel area is in operation; the empty barrel area stimulation area is not occupied; the employee feedback area is not occupied; the employee inventory is empty; the employee's physical strength is greater than 40; or
[0111] f2: The empty barrel area is in operation; the empty barrel area stimulation area is not occupied; the employee feedback area is not occupied; the employee inventory is empty; the empty barrel area operation position coordinates and the employee position coordinates coincide; or
[0112] f3: The empty bucket area is in a waiting state; the empty bucket area stimulation area is not occupied; the employee feedback area is not occupied; the employee inventory is an empty bucket; or
[0113] f4: The empty barrel area is in a waiting-to-recovery state; the empty barrel area stimulation area is not occupied; the employee feedback area is not occupied; the empty barrel area operation position coordinates coincide with the employee position coordinates.
[0114] g(Storage area - employees):
[0115] g1: The storage area is vacant; the storage area and the stimulation area are not occupied; the employee feedback area is not occupied; the employee inventory is a barrel containing products; or
[0116] g2: The storage area is vacant; the storage area stimulation area is not occupied; the employee feedback area is not occupied; the employee inventory is a barrel containing products; the storage area operation position coordinates and the employee position coordinates coincide; or
[0117] g3: The storage area is in the state of waiting for discharge; the storage area stimulation area is not occupied; the employee feedback area is not occupied; the employee inventory is empty; the employee's physical value is greater than 40; or
[0118] g4: The storage area is in the waiting state; the storage area stimulation area is not occupied; the employee feedback area is not occupied; the employee inventory is none; the storage area operation position coordinates coincide with the employee position coordinates.
[0119] h(rest area—staff):
[0120] h1: The rest area is vacant; the employee is vacant; the rest area stimulation area is not occupied; the employee feedback area is not occupied; the employee inventory is empty; or
[0121] h2: The rest area is vacant; the employee is vacant; the rest area stimulation area is not occupied; the employee feedback area is not occupied; the employee inventory is empty; the rest area operation position coordinates coincide with the employee position coordinates.
[0122] If a new stimulus feedback chain is formed, the working subset and the non-working subset are updated. After the update is completed, the response states of the class neurons in the updated working subset are distinguished to obtain the self-response state sub-subset and the other-response state sub-subset. For the class neurons in the self-response state sub-subset, the sub-mapping f of the mapping F is determined according to the response mapping rule set in advance. i , then calculate the attribute parameter of this type of neuron M(t'+Δt)=f i M(t').
[0123] Specifically, the response mapping rules include:
[0124] Mixer: If the mixer is in working state and the hourglass is greater than 0, the hourglass will deduct Δt; the non-fixed cost 1 will increase by 100; or
[0125] When the mixer is in working state and the time hourglass is less than or equal to 0, the mixer changes to the state of waiting for discharge.
[0126] Raw material area: if the raw material area is in preparation state and the time hourglass is greater than 0, then the time hourglass of the raw material area will be deducted by Δt; or
[0127] If the raw material area is in the preparation state and the time hourglass is less than or equal to 0, the raw material area becomes vacant; the non-fixed cost 2 increases by 500.
[0128] Employee: If the employee is in the transport state, the "D algorithm" is used to calculate the shortest path between the employee and the storage area coordinates, that is, from the current coordinates to the target coordinates, use ↑→↓←, the employee coordinates are (i, j), ↑ then j increases by 1, ↓ then j decreases by 1, ← then i decreases by 1, → then i increases by 1, and the employee's movement direction is determined according to the moving direction, and the employee's physical strength is deducted by 0.3; or
[0129] If the employee's coordinates coincide with the rest area's coordinates, the employee's physical strength increases by 5.
[0130] For the class neurons in the sub-subset of his response state, the sub-mapping f of each class neuron in the new stimulus feedback chain is determined according to the stimulus feedback mapping table shown in Table 2 corresponding to Table 1. i , and calculate the corresponding neuron-like attribute parameter M(t'+Δt)=f i M(t').
[0131] Table 2 Stimulus feedback mapping table
[0132] Neuron-like Blender staff Raw material area Empty barrel area Storage area Living Area Blender N / A a’ b' c' N / A N / A staff a' N / A d' f' g' h' Raw material area b' d' N / A e' N / A N / A Empty barrel area c' f' e' N / A N / A N / A Storage area N / A g' N / A N / A N / A N / A Living Area N / A h' N / A N / A N / A N / A
[0133] In the table, N / A indicates that there is no such mapping relationship.
[0134] The mapping relationships a'-h' are:
[0135] a'(mixer - employee):
[0136] Condition a1 is met: the employee changes to the transporting state; or
[0137] Condition a2 is met: the mixer changes to the running state; the mixer time hourglass is reset to working time 10; the employee changes to the vacant state; the employee's inventory changes to an empty bucket; the employee's chain changes to the destroyed state; or
[0138] Condition a3 is met: the employee changes to the transporting state; or
[0139] Condition a4 is met: the mixer changes to an empty state; the employee changes to an empty state; the employee's inventory is a barrel containing products; the employee's chain changes to a destroyed state.
[0140] b'(Mixer-Raw Material Area):
[0141] Condition b is met: the raw material area is transformed into the operating state.
[0142] c'(Mixer-empty barrel area):
[0143] Satisfy condition c: The empty barrel area changes to the operating state.
[0144] d'(Raw material area - employees):
[0145] Satisfy condition d1: The employee changes to the transporting state; or
[0146] Condition d2 is met: the raw material area changes to the preparation state; the raw material area time hourglass is reset to working time 5; the employee changes to the vacant state; the employee's inventory is a barrel of raw materials; the employee's chain changes to the destruction state.
[0147] e'(Raw material area - empty barrel area):
[0148] Condition e is met: the raw material area is transformed into working state.
[0149] f'(Empty barrel area - employees):
[0150] Satisfy condition f1: The employee changes to the transport state; or
[0151] Condition f2 is met: the empty barrel area changes to the waiting state; the employee changes to the vacant state; the employee's inventory is an empty barrel; the employee's chain changes to the destroyed state; or
[0152] Condition f3 is met: the employee changes to the transporting state; or
[0153] Satisfy condition f4: the empty barrel area changes to a vacant state; the employee changes to a vacant state; the empty barrel area inventory is an empty barrel; the employee inventory is nothing; the employee's chain changes to a destroyed state.
[0154] g'(Storage area - employees):
[0155] Satisfy condition g1: The employee changes to the transporting state; or
[0156] Condition g2 is met: the product placement area changes to the waiting state; the product placement area time hourglass is reset to working time 10; the product placement area inventory is a barrel containing products; the employee inventory is empty; the employee's chain changes to the destroyed state; or
[0157] Condition g3 is met: the employee changes to the transporting state; or
[0158] Condition g4 is met: the product placement area becomes vacant; the employee becomes vacant; the product placement area inventory is empty; the employee inventory is an empty barrel; the employee's chain becomes destroyed.
[0159] h'(rest area - staff):
[0160] Satisfy condition h1: The employee changes to the transporting state; or
[0161] Condition h2 is met: the rest area is changed to working state; the employee is changed to waiting for recovery state; the employee's chain is changed to destroyed state.
[0162] Next, traverse the working subset and determine whether the conditions for destroying the stimulus feedback are met according to the stimulus feedback termination table shown in Table 3: If the conditions are met, the stimulus feedback is terminated, the stimulus area and the feedback area number are cleared, and the upstream class neuron is found based on the number. The stimulus area and the feedback area number are also cleared until the class neuron feedback area on the same chain is in an unoccupied state. At this time, the entire stimulus feedback chain is destroyed.
[0163] Table 3 Stimulation feedback termination table
[0164] Neuron-like Blender staff Raw material area Empty barrel area Storage area Living Area Blender N / A o N / A N / A N / A N / A staff o N / A o o o o Raw material area N / A o N / A N / A N / A N / A Empty barrel area N / A o N / A N / A N / A N / A Storage area N / A o N / A N / A N / A N / A Living Area N / A o N / A N / A N / A N / A
[0165] In the table, N / A means that there is no termination condition for this situation.
[0166] The termination condition represented by o is: if the employee's chain is in a destructible state, the stimulus feedback chain is destroyed and the employee's chain is transformed into an indestructible state.
[0167] In this process, the cost and profit of each cycle are calculated: the fixed cost of each class of neurons is J i , calculate the total fixed cost J = ∑J i =10000+0+800+800+800+800=13200, where i represents the legend number of the class neuron; the non-fixed cost 1 of each class neuron is calculated as O i , calculate the total non-fixed cost 1 as O = ∑O i ; Calculate the non-fixed cost 2 of each class of neurons as P i , calculate the total non-fixed cost 2 as P = ∑P i ; Calculate the profit of each class of neurons as Y i , calculate the total profit as Y = ∑Y i . Get Fig.11 The cost curves shown and Fig.12 The profit curve is shown.
[0168] After obtaining the above cost curve and profit curve, you can compare them with the preset production line target. If they do not meet expectations, you can adjust the design, layout and process flow of the initial CAD drawings to achieve expectations. You can also compare the data after simulation of different initial CAD drawings, and adjust the design, layout and process flow of the initial CAD drawings based on this to find the optimal solution for high efficiency of the factory production line.
[0169] When making adjustments, an exhaustive method can be used to adjust various influencing factors. Preferably, a genetic algorithm can be introduced to determine which are the invariant influencing factors. For example, placing the coater horizontally in the middle is a placement solution with high fitness. This factor is fixed and other influencing factors are adjusted to speed up the optimization process and save the workload and efficiency of adjustments when seeking the optimal solution.
[0170] Traditional simulation, whether it is mechanics, thermal management, electrochemistry, or materials, only explores the local optimal solution in a certain aspect, while the simulation method in this specific example comprehensively considers all performance factors, considers the cost of putting this solution into production, and reforms the existing production of people, machines, materials, methods, and environment, and finally seeks a global optimal solution. Adjusting the factory production line based on the simulation method provided in this specific example not only reduces the simulation cost while ensuring the accuracy of the simulation, but also obtains the optimal adjustment plan and maximizes economic benefits.
[0171] The implementation of the above specific application is only an example, and the remaining implementation methods will not be described in detail one by one.
[0172] Based on the same inventive concept, the embodiment of the present invention further provides a factory simulation device. Since the principle of solving the problem by the factory simulation device is similar to that of the factory simulation method, the implementation of the factory simulation device can refer to the implementation of the factory simulation method, and the repeated parts will not be repeated. The specific structure is as follows: Fig.13 As shown:
[0173] A neuron-like determination module 1301 is used to obtain a plurality of production factors running in a working area of a factory production line, and determine a plurality of neuron-like factors and attribute parameters of each neuron-like factor for factory simulation according to the plurality of production factors;
[0174] The feedback stimulation simulation module 1302 is used to perform the following operations cyclically at preset time intervals to determine the attribute parameters of each neuron-like class at each moment in the factory simulation period:
[0175] Determine the feedback stimulation chain formed between multiple neuron-like neurons at the current moment according to the attribute parameters of each neuron-like neuron at the current moment, and determine the attribute parameters of each neuron-like neuron at the next moment according to the feedback stimulation chain; wherein the next moment is separated from the current moment by the preset time interval;
[0176] The simulation result determination module 1303 is used to determine the factory simulation result according to the attribute parameters of each neuron-like object at each moment in the factory simulation period.
[0177] In a specific embodiment, the neuron-like determination module 1301 is specifically used to:
[0178] The multiple production factors are grouped according to their types, and based on the grouping conditions, the multiple production factors are abstracted into multiple class neurons, and the attribute parameters of each class neuron are determined.
[0179] Specifically, the neuron-like determination module 1301 is specifically used for:
[0180] According to the grouping situation, the classification type of the neuron is determined;
[0181] According to the classification type, the class neurons corresponding to each production factor are grouped and numbered to obtain a set consisting of multiple class neurons.
[0182] In a specific embodiment, the attribute parameters include at least one or any combination of: a stimulation area occupancy parameter, a feedback area occupancy parameter, a production status parameter, a cost parameter, and a profit parameter.
[0183] Furthermore, the feedback stimulation simulation module 1302 is specifically used for:
[0184] Traversing a set composed of multiple neuron-like neurons, determining the feedback stimulation chain that is currently working according to the stimulation area occupancy parameter, feedback area occupancy parameter and production state parameter of each neuron-like neuron in the set at the current moment, and obtaining a working subset composed of neuron-like neurons included in the working feedback stimulation chain, and a non-working subset;
[0185] Traverse the non-working subset, and according to the stimulation area occupancy parameters, feedback area occupancy parameters and production state parameters of each class of neurons in the non-working subset, as well as the preset stimulation feedback formation condition parameters, obtain the newly constructed feedback stimulation chain at the current moment, and update the working subset and the non-working subset;
[0186] Traversing the updated working subset, and determining the feedback stimulation chain for terminating the work at the current moment according to the stimulation area occupancy parameter, feedback area occupancy parameter and production state parameter of each class neuron in the working subset, as well as the preset stimulation feedback termination condition parameter;
[0187] According to the feedback stimulation chain currently in operation, the newly constructed feedback stimulation chain currently in operation and the feedback stimulation chain currently terminated, the feedback stimulation chain formed between the multiple neuron-like chains currently in operation is determined.
[0188] In a specific embodiment, the feedback stimulation simulation module 1302 is further specifically used for:
[0189] According to the feedback stimulation chain formed between the multiple neuron-like neurons at the current moment, a mapping relationship between the attribute parameters of each neuron-like neuron at the next moment and the attribute parameters of each neuron-like neuron at the current moment is determined;
[0190] According to the above mapping relationship and the attribute parameters of each neuron-like at the current moment, the attribute parameters of each neuron-like at the next moment are determined.
[0191] Accordingly, the simulation result determination module 1303 is specifically used for:
[0192] According to the cost parameters and profit parameters of each neuron-like object at each moment in the factory simulation period, the simulation cost data and simulation profit data of the factory operation corresponding to the factory simulation period are determined to obtain the factory simulation result.
[0193] In addition, the factory simulation device provided in the specific embodiment is used to further reduce the amount of simulation calculations. Fig.14 As shown, in Fig.13 On the basis of
[0194] The area division module 1401 is used to:
[0195] Get working area data of factory production lines;
[0196] According to the working area data, the working area is gridded to obtain a grid division for factory simulation; the grid division is divided into regions to obtain a movable region and an immovable region;
[0197] According to the grid division, movable area and immovable area, the attribute parameters of each neuron class are determined.
[0198] An embodiment of the present invention further provides a computer device, Fig.15 Schematic diagram of a computer device in an embodiment of the present invention. The computer device can implement all steps in the factory simulation method in the above embodiment. The computer device specifically includes the following contents:
[0199] Processor (processor) 1501, memory (memory) 1502, communication interface (CommunicationsInterface) 1503 and communication bus 1504;
[0200] The processor 1501, the memory 1502, and the communication interface 1503 communicate with each other through the communication bus 1504; the communication interface 1503 is used to realize information transmission between related devices;
[0201] The processor 1501 is used to call the computer program in the memory 1502, and the processor implements the factory simulation method in the above embodiment when executing the computer program.
[0202] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for executing the above-mentioned factory simulation method.
[0203] In summary, the factory simulation method and device provided by the embodiments of the present invention have the following advantages:
[0204] In an embodiment of the present invention, by acquiring multiple production factors running in the working area of the factory production line, multiple class neurons and attribute parameters of each class neuron for factory simulation are determined according to the multiple production factors; according to the preset time interval, the following operations are performed cyclically to determine the attribute parameters of each class neuron at each moment in the factory simulation period: according to the attribute parameters of each class neuron at the current moment, the feedback stimulation chain formed between the multiple class neurons at the current moment is determined, and the attribute parameters of each class neuron at the next moment are determined according to the feedback stimulation chain; wherein the next moment is separated from the current moment by the above preset time interval; according to the attribute parameters of each class neuron at each moment in the factory simulation period, the factory simulation result is determined. By abstracting the production factors of the factory production line into class neurons, the operation of the factory production line is simulated based on the feedback stimulation chain between class neurons to simulate the real production of the factory, thereby facilitating the optimization of the factory production line design.
[0205] Although the present invention provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, in a parallel processor or multi-threaded processing environment).
[0206] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, devices (systems) or computer program products. Therefore, the embodiments of this specification may take the form of complete hardware embodiments, complete software embodiments or embodiments combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0207] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0208] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0209] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0210] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. In this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such a process, method, article or device. The orientation or position relationship indicated by the terms "upper", "lower", etc. is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. Unless otherwise expressly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other in the absence of conflict. The present invention is not limited to any single aspect, nor to any single embodiment, nor to any combination and / or permutation of these aspects and / or embodiments. Moreover, each aspect and / or embodiment of the present invention can be used alone or in combination with one or more other aspects and / or embodiments thereof.
[0211] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.
Claims
1. A factory simulation method, characterized in that: include: Acquire multiple production factors running in a working area of a factory production line, and determine multiple neuron-like factors and attribute parameters of each neuron-like factor for factory simulation according to the multiple production factors; At preset time intervals, the following operations are performed cyclically to determine the attribute parameters of each neuron-like class at each moment in the factory simulation period: Determine, according to the attribute parameters of each neuron-like at the current moment, a feedback stimulation chain formed between a plurality of neuron-like at the current moment, and determine, according to the feedback stimulation chain, the attribute parameters of each neuron-like at the next moment; wherein the next moment is separated from the current moment by the preset time interval; Determine the factory simulation result according to the attribute parameters of each neuron-like object at each moment in the factory simulation period; The step of determining a plurality of neuron-like components and attribute parameters of each neuron-like component for factory simulation according to the plurality of production factors includes: The multiple production factors are grouped according to type, and according to the grouping situation, the multiple production factors are abstracted into multiple class neurons, and the attribute parameters of each class neuron are determined; wherein the attribute parameters of the class neuron include at least: one or any combination of stimulation area occupancy parameters, feedback area occupancy parameters, production status parameters, cost parameters and profit parameters; the stimulation area occupancy parameters are used to indicate the next level class neuron to be stimulated by the class neuron; the feedback area occupancy parameters are used to indicate the class neuron to which the class neuron feeds back the results; the production status parameters are used to characterize the relevant status of the class neuron in the production process, and the relevant status includes working status, loading status, running time, fault status, movement direction and trajectory; the cost parameters and profit parameters are used to characterize the current cost required and the profit that can be brought by the class neuron; The step of determining the feedback stimulation chain formed between multiple neuron-like neurons at the current moment according to the attribute parameters of each neuron-like neuron at the current moment includes: Traversing a set composed of multiple neuron-like neurons, determining the feedback stimulation chain that is currently working according to the stimulation area occupancy parameter, feedback area occupancy parameter and production state parameter of each neuron-like neuron in the set at the current moment, and obtaining a working subset composed of neuron-like neurons included in the working feedback stimulation chain, and a non-working subset; Traversing the non-working subset, according to the stimulation area occupancy parameter, feedback area occupancy parameter and production state parameter of each class neuron in the non-working subset, and the preset stimulation feedback formation condition parameter, a newly constructed feedback stimulation chain at the current moment is obtained, and the working subset and the non-working subset are updated; Traversing the updated working subset, and determining the feedback stimulation chain for terminating the work at the current moment according to the stimulation area occupancy parameter, feedback area occupancy parameter and production state parameter of each class of neurons in the updated working subset, as well as the preset stimulation feedback termination condition parameter; Determine the feedback stimulation chain formed between multiple neuron-like chains at the current moment according to the feedback stimulation chain currently in operation, the newly constructed feedback stimulation chain at the current moment, and the feedback stimulation chain terminated at the current moment; Determining the attribute parameters of each neuron-like class at the next moment according to the feedback stimulation chain includes: Determine, according to the feedback stimulation chain, a mapping relationship between the attribute parameters of each neuron-like object at the next moment and the attribute parameters of each neuron-like object at the current moment; According to the mapping relationship and the attribute parameters of each neuron-like class at the current moment, the attribute parameters of each neuron-like class at the next moment are determined.
2. The factory simulation method according to claim 1, characterized in that: According to the grouping situation, multiple production factors are abstracted into multiple class neurons, including: According to the grouping situation, the classification type of the neuron is determined; According to the classification type, the class neurons corresponding to each production factor are grouped and numbered to obtain a set consisting of multiple class neurons.
3. The factory simulation method according to claim 2, characterized in that: According to the attribute parameters of each neuron-like object at each moment in the factory simulation period, the factory simulation results are determined, including: According to the cost parameters and profit parameters of each neuron-like object at each moment in the factory simulation period, the simulation cost data and simulation profit data of the factory operation corresponding to the factory simulation period are determined to obtain the factory simulation result.
4. The factory simulation method according to claim 1, characterized in that: Also includes: Get working area data of factory production lines; According to the working area data, the working area is gridded to obtain a grid division for factory simulation; Dividing the grid into regions to obtain movable regions and immovable regions; According to the grid divisions, movable areas and immovable areas, attribute parameters of each neuron class are determined.
5. A factory simulation device, characterized in that: include: A neuron-like determination module, used to obtain a plurality of production factors running in a working area of a factory production line, and determine a plurality of neuron-like components and attribute parameters of each neuron-like component for factory simulation according to the plurality of production factors; The feedback stimulation simulation module is used to perform the following operations cyclically at preset time intervals to determine the attribute parameters of each neuron-like class at each moment in the factory simulation period: Determine, according to the attribute parameters of each neuron-like at the current moment, a feedback stimulation chain formed between a plurality of neuron-like at the current moment, and determine, according to the feedback stimulation chain, the attribute parameters of each neuron-like at the next moment; wherein the next moment is separated from the current moment by the preset time interval; A simulation result determination module, used to determine the factory simulation result according to the attribute parameters of each neuron-like object at each moment in the factory simulation period; The neuron-like determination module is further used for: The multiple production factors are grouped according to type, and according to the grouping situation, the multiple production factors are abstracted into multiple class neurons, and the attribute parameters of each class neuron are determined; wherein the attribute parameters of the class neuron include at least: one or any combination of stimulation area occupancy parameters, feedback area occupancy parameters, production status parameters, cost parameters and profit parameters; the stimulation area occupancy parameters are used to indicate the next level class neuron to be stimulated by the class neuron; the feedback area occupancy parameters are used to indicate the class neuron to which the class neuron feeds back the results; the production status parameters are used to characterize the relevant status of the class neuron in the production process, and the relevant status includes working status, loading status, running time, fault status, movement direction and trajectory; the cost parameters and profit parameters are used to characterize the current cost required and the profit that can be brought by the class neuron; The feedback stimulation simulation module is also used for: Traversing a set composed of multiple neuron-like neurons, determining the feedback stimulation chain that is currently working according to the stimulation area occupancy parameter, feedback area occupancy parameter and production state parameter of each neuron-like neuron in the set at the current moment, and obtaining a working subset composed of neuron-like neurons included in the working feedback stimulation chain, and a non-working subset; Traversing the non-working subset, according to the stimulation area occupancy parameter, feedback area occupancy parameter and production state parameter of each class neuron in the non-working subset, and the preset stimulation feedback formation condition parameter, a newly constructed feedback stimulation chain at the current moment is obtained, and the working subset and the non-working subset are updated; Traversing the updated working subset, and determining the feedback stimulation chain for terminating the work at the current moment according to the stimulation area occupancy parameter, feedback area occupancy parameter and production state parameter of each class of neurons in the updated working subset, as well as the preset stimulation feedback termination condition parameter; Determine the feedback stimulation chain formed between multiple neuron-like chains at the current moment according to the feedback stimulation chain currently in operation, the newly constructed feedback stimulation chain at the current moment, and the feedback stimulation chain terminated at the current moment; The feedback stimulation simulation module is also used for: Determining the attribute parameters of each neuron-like class at the next moment according to the feedback stimulation chain includes: Determine, according to the feedback stimulation chain, a mapping relationship between the attribute parameters of each neuron-like object at the next moment and the attribute parameters of each neuron-like object at the current moment; According to the mapping relationship and the attribute parameters of each neuron-like class at the current moment, the attribute parameters of each neuron-like class at the next moment are determined.
6. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.
7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program for executing the method according to any one of claims 1 to 4.
