AMR task scene equipment parameter simulation generation method and device and storage medium

Abstract

The invention relates to an AMR task scene equipment parameter simulation generation method and device and a storage medium, and is applied to the technical field of digital twinning, and the method comprises the steps: determining equipment participating in a task scene through determining task processes of different AMR task scenes, and obtaining an interactive relationship between every two pieces of equipment (including AMR) participating in the task scene through obtaining the interactive relationship between every two pieces of equipment (including AMR) participating in the task scene; determining a coupling relationship between any two devices, screening N devices having strong coupling relationships with the AMR, and generating a sampling parameter combination of the AMR and the N devices according to historical operation data of the devices and the coupling relationships; a digital twinborn model of an AMR task scene is constructed through a digital twinborn technology, in the digital twinborn model, simulation operation of a task process is performed on different parameter combinations, and a reliability score corresponding to each parameter combination is obtained, so that an optimal parameter combination is screened out, and the reliability of the AMR task scene is improved. And updating the real AMR and the parameters of the equipment according to the optimal parameter combination.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twins, and particularly to a method, device, and storage medium for simulating and generating device parameters in an AMR task scenario. Background Art

[0002] An autonomous mobile robot (AMR) is an industrial device that can automatically travel along a preset route. It combines computer hardware technology, parallel and distributed processing technology, automatic control technology, and sensor technology, and can accurately and efficiently complete handling tasks, usually used for handling goods in factories or warehouses.

[0003] 3D simulation technology uses 3D software to model, render, and then create animations for the AMR working environment. For example, simulation functions provided by software such as Flexsim and plant simulation can simulate the operation of the working environment by inputting certain initial data. For instance, a 3D visualization simulation scheme for an automated warehousing and logistics system is given in "Research on Visualization Simulation and Optimization of Automated Warehousing and Logistics Systems", and the reliability of the system is evaluated through simulation results.

[0004] However, traditional simulation methods rely heavily on experience and industry knowledge when setting parameters. After expert experience and on-site research, they are then set. However, due to the differences between different AMR working environment solutions, the parameters set only based on experience often do not fit the scenario and task, and cannot guarantee stable performance in multiple scenarios to be simulated, and cannot fully exert the maximum efficiency of the AMR working environment, resulting in inaccurate evaluation. In addition, a logistics warehouse is a multi-factor complex system that requires setting a large number of parameters, and there are multi-factor couplings between the parameters. Traditional methods usually set parameters independently one by one, ignoring the connections between the parameters. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a method, device, and storage medium for simulating and generating device parameters in an AMR task scenario to solve the problems in the prior art that rely heavily on experience and industry knowledge when setting parameters, require expert experience and on-site research before setting, but due to the differences between different AMR working environment solutions, the parameters set only based on experience often do not fit the scenario and task, and at the same time solve the problem that a logistics warehouse is a multi-factor complex system that requires setting a large number of parameters, and there are multi-factor couplings between the parameters, and traditional methods usually set parameters independently one by one, ignoring the connections between the parameters.

[0006] According to the first aspect of the embodiments of the present invention, a method for simulating and generating device parameters in an AMR task scenario is provided. The method includes: Determine the task process in any AMR task scenario, and determine the devices participating in the task scenario according to the task process. The devices include AMRs and other devices; Obtain the task dependency between any two devices according to the interaction relationship between the devices participating in the task scenario; obtain the spatial overlap rate between any two devices according to the floor area of the devices participating in the task scenario; obtain the energy exchange rate between any two devices according to the energy type interaction intensity between the devices participating in the task scenario; Obtain the coupling strength between any two devices according to the task dependency, spatial overlap rate, and energy exchange rate between any two devices; Select the coupling strength between any device and the AMR among the coupling strengths between any two devices, sort the coupling strengths between any device and the AMR, and select the N devices with the highest coupling strength with the AMR; Obtain the historical operation data of the AMR and the N devices, and generate the final sampling parameter combinations of the AMR and the N devices according to the historical operation data and the coupling strength; Build a digital twin model of the AMR working environment. In the digital twin model, set the parameters of the virtual AMR and the N virtual devices according to the final sampling parameter combinations, and execute the task process in the AMR task scenario in the digital twin model; Obtain the reliability scores under each parameter combination respectively, and select the parameter combination with the highest reliability score as the optimal parameter combination; Set the real AMR and the N real devices according to the optimal parameter combination.

[0007] Preferably, The generating the final sampling parameter combinations of the AMR and the N devices according to the historical operation data and the coupling strength includes: Obtain the initial parameter ranges of the AMR and the N devices according to the historical operation data; Adopt the Sobol sequence parameter generation method to generate the initial sampling parameter combinations of the AMR and the N devices within the initial parameter ranges of the AMR and the N devices, and the initial sampling parameters of any two devices satisfy the corresponding coupling relationship; Calculate the sensitivity indices of the N devices according to the initial sampling parameters of the N devices, sort the sensitivity indices of the N devices from largest to smallest, take the AMR as the first sampling item, and take the sorting of the sensitivity indices of the N devices as the sampling priorities of the N devices; Again, adopt the Sobol sequence parameter generation method. According to the sampling priority, within the initial parameter ranges of the AMR and N devices, successively generate the final sampling parameter combinations of the AMR and N devices, and the final sampling parameters of any two devices satisfy the corresponding coupling relationship.

[0008] Preferably, The calculation of the sensitivity index of N devices according to the initial sampling parameters of N devices includes: Set the task metrics of the AMR task scenario, use the task metrics as the system output, obtain the variance caused by any initial sampling parameter alone to the task metrics, and obtain the variance caused by the interaction of any initial sampling parameter with other initial sampling parameters to the task metrics; According to the variance caused by any initial sampling parameter alone to the task metrics and the variance caused by the interaction of any initial sampling parameter with other initial sampling parameters to the task metrics, obtain the variance of the system output; According to the variance caused by any initial sampling parameter alone to the task metrics and the variance of the system output, obtain the sensitivity metric of any initial sampling parameter; Take the sensitivity metric of the initial sampling parameter as the sensitivity index of the corresponding device.

[0009] Preferably, The obtaining of the task dependence degree between any two devices according to the interaction relationship between the devices participating in the task scenario includes: Obtain the direct interaction times of any two devices participating in the task scenario in the task process, and respectively obtain the action times of any two devices in the task process; according to the direct interaction times of any two devices in the task process and the action times of any two devices in the task process, obtain the process dependence coefficient; Set the weight of each resource, and obtain the sharing degree of any two devices to any resource; according to the weight of any resource and the sharing degree of any two devices to any resource, obtain the resource sharing degree; Set the attenuation coefficient, and set the ideal time interval of the actions of any two devices, and obtain the actual time interval of the actions of any two devices; according to the attenuation coefficient, the ideal time interval of the actions of any two devices and the actual time interval, obtain the time coupling coefficient; Respectively set the weights of the process dependence coefficient, the resource sharing degree and the time coupling coefficient; According to the weights of the process dependence coefficient, the resource sharing degree and the time coupling coefficient, perform weighted fusion on the process dependence coefficient, the resource sharing degree and the time coupling coefficient to obtain the task dependence degree between any two devices.

[0010] Preferably, The obtaining of the sharing degree of any two devices for any resource includes: Obtaining the time when any two devices use the same resource respectively, and obtaining the intersection and union of the time when any two devices use the same resource respectively. Dividing the intersection of the time when any two devices use the same resource by the union, the sharing degree of any two devices for any resource is obtained.

[0011] Preferably, The obtaining of the spatial overlap rate between any two devices according to the floor areas of the devices participating in the task scenario includes: Obtaining the floor areas of any two devices respectively, obtaining the intersection of the floor areas of any two devices according to the floor areas of any two devices, and dividing the intersection of the floor areas of any two devices by the smaller floor area of any two devices, the spatial overlap rate between any two devices is obtained.

[0012] Preferably, The obtaining of the energy exchange rate between any two devices according to the energy type interaction intensity between the devices participating in the task scenario includes: Setting the weight of each energy type, obtaining the interaction intensity of any two devices on the same energy type, and obtaining the energy exchange rate between any two devices according to the weight of any energy type and the interaction intensity of any two devices on the same energy type; The obtaining of the interaction intensity of any two devices on the same energy type includes: Obtaining the time ratios of any two devices using the same energy type respectively; and obtaining the intersection and union of the time ratios of any two devices using the same energy type respectively. Dividing the intersection of the time ratios of any two devices using the same energy type by the union, the interaction intensity of any two devices on the same energy type is obtained.

[0013] Preferably, The obtaining of the reliability score for each parameter combination includes: Obtaining the total number of times of executing the AMR task scenario within a preset time period for each parameter combination, and the number of times of successfully completing the AMR task scenario within the preset time period. Dividing the number of times of successfully completing the AMR task scenario within the preset time period by the total number of times of executing the AMR task scenario within the preset time period to obtain the task completion rate; the total number of times of executing the AMR task scenario within the preset time period is the sum of the number of times of successfully completing the AMR task scenario within the preset time period and the number of times of failing to complete the AMR task scenario; Obtaining the average time of successfully completing the AMR task scenario within a preset time period for each parameter combination to obtain the task completion time; Obtain the total power consumption of the devices participating in the task scenario within a preset time period for each parameter combination, multiply the total power consumption by the unit price of electricity to obtain the operating cost; Set the utilization weight of the AMR in different operating states, obtain the time proportion of the AMR in different operating states within a preset time period for each parameter combination, and obtain the AMR device utilization rate according to the utilization weight and time proportion of the AMR in different operating states; Obtain the floor area and total floor area of the devices participating in the task scenario for each parameter combination, and divide the floor area of the devices participating in the task scenario by the total floor area to obtain the space utilization rate; Obtain the number of failures of the devices participating in the task scenario for each parameter combination, and obtain the failure frequency index according to the number of failures of the devices participating in the task scenario; Perform dimensionless processing on the task completion rate, task completion time, operating cost, AMR device utilization rate, space utilization rate, and failure frequency index, and fuse the dimensionless processed indicators according to the preset weight values of each indicator to obtain the reliability score for each parameter combination.

[0014] According to the second aspect of the embodiments of the present invention, there is provided an AMR task scenario device parameter simulation generation device, and the device includes: A process determination module: used to determine the task process in any AMR task scenario, and determine the devices participating in the task scenario according to the task process, where the devices include AMRs and other devices; A device relationship acquisition module: used to obtain the task dependence between any two devices according to the interaction relationship between the devices participating in the task scenario; obtain the space overlap rate between any two devices according to the floor area of the devices participating in the task scenario; obtain the energy exchange rate between any two devices according to the energy type interaction intensity between the devices participating in the task scenario; A coupling strength acquisition module: used to obtain the coupling strength between any two devices according to the task dependence, space overlap rate, and energy exchange rate between any two devices; A coupling screening module: used to select the coupling strength between any device and the AMR among the coupling strengths between any two devices, sort the coupling strengths between any device and the AMR, and select the N devices with the highest coupling strength with the AMR; A parameter generation module: used to obtain the historical operation data of the AMR and the N devices, and generate the final sampling parameter combination of the AMR and the N devices according to the historical operation data and the coupling strength; Simulation running module: used to build a digital twin model of the AMR working environment. In the digital twin model, the parameters of the virtual AMR and N virtual devices are set according to the final sampling parameter combination, and the task process in the AMR task scenario is executed in the digital twin model; Parameter screening module: used to obtain the reliability scores under each parameter combination respectively, and select the parameter combination with the highest reliability score as the optimal parameter combination; Calibration module: used to set the real AMR and N real devices according to the optimal parameter combination.

[0015] According to the third aspect of the embodiments of the present invention, a storage medium is provided. The storage medium stores a computer program, and when the computer program is executed by a main controller, each step in the above method is implemented.

[0016] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: In this application, by determining the task processes of different task scenarios of the AMR, the devices participating in the task scenarios are determined. By obtaining the interaction relationships between two devices (including the AMR) participating in the task scenarios, the coupling relationships between any two devices are determined, and N devices with strong coupling relationships with the AMR are screened. Sampling parameter combinations of the AMR and N devices are generated according to the historical operation data and coupling relationships of the devices; through digital twin technology, a digital twin model of the AMR task scenario is built. In the digital twin model, the task processes are simulated and run for different parameter combinations respectively, and the reliability scores corresponding to each parameter combination are obtained, so as to screen out the optimal parameter combination, and update the parameters of the real AMR and devices according to the optimal parameter combination; through the solution of this application, different task scenarios can be virtually run in the digital twin model, not limited to a single task scenario, and in the process of parameter generation, the coupling relationships between parameters are fully considered, avoiding the problem that traditional methods set each parameter independently and ignore the internal relationships between parameters.

[0017] It should be understood that the above general description and subsequent detailed description are only exemplary and explanatory, and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present invention, and are used together with the specification to explain the principles of the present invention.

[0019] Figure 1 is a schematic flowchart of a method for simulating and generating device parameters in an AMR task scenario shown according to an exemplary embodiment; Figure 2It is a schematic diagram showing the composition of reliability indicators according to another exemplary embodiment; Figure 3 It is a system schematic diagram of a device parameter simulation generation device for an AMR task scenario according to another exemplary embodiment; In the drawings: 1 - Process determination module, 2 - Device relationship acquisition module, 3 - Coupling strength acquisition module, 4 - Coupling screening module, 5 - Parameter generation module, 6 - Simulation operation module, 7 - Parameter screening module, 8 - Calibration module. Detailed implementation mode

[0020] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present invention. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0021] Embodiment 1 Figure 1 It is a flowchart of a method for simulating and generating device parameters for an AMR task scenario according to an exemplary embodiment, as Figure 1 shown, the method includes: S1. Determine the task process in any AMR task scenario, and determine the devices participating in the task scenario according to the task process. The devices include AMRs and other devices; S2. Obtain the task dependency between any two devices according to the interaction relationship between the devices participating in the task scenario; obtain the spatial overlap rate between any two devices according to the floor area of the devices participating in the task scenario; obtain the energy exchange rate between any two devices according to the energy type interaction intensity between the devices participating in the task scenario; S3. Obtain the coupling strength between any two devices according to the task dependency, spatial overlap rate, and energy exchange rate between any two devices; S4. Select the coupling strength between any device and the AMR among the coupling strengths between any two devices, sort the coupling strengths between any device and the AMR, and select the N devices with the highest coupling strength with the AMR; S5. Obtain the historical operation data of the AMR and the N devices, and generate the final sampling parameter combination of the AMR and the N devices according to the historical operation data and the coupling strength; S6. Construct a digital twin model of the AMR working environment. In the digital twin model, set the parameters of the virtual AMR and N virtual devices according to the final sampled parameter combination, and execute the task process in the AMR task scenario in the digital twin model; S7. Obtain the reliability scores under each parameter combination respectively, and select the parameter combination with the highest reliability score as the optimal parameter combination; S8. Set the real AMR and N real devices according to the optimal parameter combination; It can be understood that what needs to be determined first in this application is the task process of the AMR task scenario. According to the task process, the participating devices (including AMR and other devices) can be determined. Then, in order to accurately calculate other parameters, the relationships such as spatio-temporal constraints, energy interaction, and task coupling among physical devices need to be transformed into a quantifiable mathematical model: construct a dynamic influence network among devices, where the matrix elements represent the coupling strength (0-1) between devices. To simplify the analysis process, one device corresponds to one main parameter, and the correlation between parameters can be obtained by analyzing the coupling relationship between devices; The coupling strength between devices is determined by three factors: task dependence degree, space overlap rate, and energy exchange rate; among them, the task dependence degree is obtained by weighted calculation of the process dependence coefficient, resource sharing degree, and time coupling coefficient. The process dependence coefficient T f measures the cooperation strength generated between devices due to the task process sequence, reflects the logical dependence relationship of devices in the task chain, and the specific expression formula is as follows:

[0022] In the formula, N ij is the device i and j the direct interaction times in the task chain, N i is the device i the number of actions in the task process, N j is the device j the number of actions in the task process; The resource sharing degree R s quantifies the interaction strength generated between devices due to sharing common resources (such as tools, materials, space), reflects the competition or cooperation degree of devices in physical resources, and the specific expression formula is as follows:

[0023] In the formula, W k is the weight of resource k (set according to scarcity), S ijk is the device i and jDegree of sharing of resource k; where S ijk is obtained by the following formula:

[0024] In the formula, U ik is the time when device i uses resource k . U jk is the time when device j uses resource k . The time coupling coefficient C t describes the cooperation intensity generated by the operation timing relationship between devices, reflecting the synchronization or dependence degree of devices in the time dimension. The specific expression formula is as follows:

[0025] In the formula, Δ t is the actual time interval between the actions executed by any two devices in the task process, and Δ t standard is the ideal time interval, that is, the optimal cooperation time of the two devices designed by the system. λ is the attenuation coefficient, which controls the sensitivity of the time difference to the coupling intensity. Usually, λ = 0.5; In summary, the calculation formula for the task dependence degree D ij is:

[0026] where the weight values α = 0.5, β = 0.3, γ = 0.2, and can be fine-tuned according to the actual situation; The spatial overlap rate S ij is calculated by the following formula:

[0027] is calculated, where S i , S j are the floor areas of device i and device j respectively; The calculation formula for the energy exchange rate E ij is:

[0028] In the formula, W k represents the weight of energy type k (set according to the energy form), and E ijk represents the interaction intensity between device i and device j in energy type k. The expression formula is as follows:

[0029] Wherein, U ik represents the time proportion of the device i using energy type k, and U jk represents the time proportion of the device j using energy type k; Finally, the task dependence, spatial overlap rate, and energy exchange rate are dimensionless processed. Then, according to the task dependence, spatial overlap rate, and energy exchange rate, the coupling strength between devices is calculated, and the adjacency matrix of device interaction relationship is constructed as follows:

[0030] Device i and device j The coupling strength C ij , and the calculation formula is:

[0031] Where α, β, γ The preset values of are 0.6, 0.3, 0.1, which can be fine-tuned as needed. For example, in an energy consumption sensitive scenario, the weight of E ij can be appropriately increased; According to the adjacency matrix of device interaction relationship, the coupling strength between each device and the AMR can be obtained. By setting a coupling strength threshold, devices with a high coupling strength with the AMR can be screened, or, the coupling strengths between each device and the AMR are sorted, and the top N devices are selected; In this embodiment, the top N devices sorted by coupling strength are selected; Obtain the historical operation data of the AMR and the selected N devices. According to the historical operation data, the initial parameter ranges of the AMR and the N devices can be determined by using kernel density estimation; Sobol sequence parameter generation: The Sobol sequence is a quasi-Monte Carlo parameter generation method that generates a low-discrepancy point set in a high-dimensional space through a deterministic algorithm. Compared with randomly generated data, its core advantages are: uniform coverage, efficient convergence, and deterministic reproducibility. The sample points are uniformly distributed, avoiding the aggregation phenomenon of randomly generated data. Under the same sample size, the integration estimation error is significantly lower than that of randomly generated data. The generated sequence is completely reproducible, facilitating debugging and verification; Using historical correlation to make the sampling parameters satisfy the coupling relationship of the previous step, reducing invalid parameter combinations. Finally, the generated parameter combinations also satisfy the constraints of space-time occupancy, improving the rationality of the parameters, and thus improving the quality of parameter generation, that is, generating the initial sampling parameters of the AMR and the N devices; Sensitivity test: Take the initial sampling parameters of N devices as input and perform variance decomposition according to the following formula:

[0032] In the formula, Var(Y) is the variance of the output Y, where V i is the variance caused by the parameter X i alone, and V ij is the variance caused by the interaction between the parameter X i and X j ; Y is the system index, such as task completion time, total energy consumption, accuracy, etc.; Use the formula:

[0033] Calculate the proportion of the impact of the individual change of the parameter X i on the output Y as the sensitivity index; Sort according to the sensitivity indices of the parameters corresponding to N devices. The larger the sensitivity index, the higher the ranking. Take the sensitivity index ranking of N devices as the sampling priority order. It should be emphasized that AMR does not participate in the sensitivity calculation, and the sampling priority of AMR is always the first in sampling; After confirming the sampling priority, use the Sobol sequence parameter generation method again to generate the final sampling parameters of AMR and N devices in sequence according to the sampling order, increase the sampling density in the high-sensitivity range, and also make the final sampling parameters meet the coupling relationship of the previous step; Digital twin system construction: Based on the digital twin theory, combined with its composition, structural relationship, and the characteristics and scenario function requirements of the application object, a digital twin model suitable for evaluating the device parameters in the AMR task environment is designed. This model consists of 4 parts, namely the physical layer, data layer, model layer, and service layer; Build geometric models of AMR, road surface, equipment, etc. according to a 1:1 ratio through 3D modeling software, and endow them with appearance shapes such as materials, colors, skins, textures, etc. Import the models into Unity and use the built-in renderer of Unity for rendering; The process is shown in the following figure: Three-dimensional model construction: 3dsMax is also a current mainstream three-dimensional modeling software. It pays more attention to the modeling of the appearance rather than the construction of the internal complex structure, but its rendering ability is very perfect and is widely used in the field of visual monitoring; Due to the complex and numerous device models in the AMR working environment, the entire scene model is divided into three parts: dynamic model, static model, and UI interaction model. The establishment of the 3D model mainly targets the dynamic and static models. Use 3dsMax to model AMR and other devices. First, complete the construction of components such as motors, drums, and bearings, and then perform the assembly of the whole machine.

[0034] Virtual scene construction: Unity3D is a globally mainstream game engine. With the continuous increase in the demand for device monitoring, more and more researchers choose Unity3D as the visualization monitoring software. Arrange the devices in the virtual environment in Unity3D according to the shape data observed in the early stage. The entire virtual scene consists of multiple parts such as AMR, other devices, roads, and buildings. Arrange the models according to their actual real - space layout and cooperation relationship, add the Light effect in Unity3D to simulate the lighting effect in the actual scene, and use the component functions provided by the software to set auxiliary devices, floors and other objects to complete the construction of the entire device scene, ensuring a high - fidelity restoration of the device. At the same time, to prevent non - realistic movements during the subsequent system operation, it is necessary to establish a hierarchical dependency relationship for all components in the virtual scene, connect all sub - components according to their subordinate relationship, and create a virtual entity that is highly consistent with the physical entity.

[0035] Behavior model construction: Collect all the real - time data generated by the movement of the physical entity and transmit it to the virtual system. After the system processes the data, use these real - time data to drive the virtual entity to perform corresponding actions, completing the real - time mapping from physical to virtual. The dynamic behaviors of the virtual entity are mainly translation, rotation, and scaling. By applying the above three transformations, the dynamic behaviors of the virtual entity can be realized. Use the Transform property in Unity to complete a series of translation, rotation, and scaling operations on the object. Through the combination of basic movements, simulate all the running actions of AMR, complete the construction of the behavior model, and realize the real - time dynamic mapping from physical entity to virtual entity.

[0036] In the virtual environment constructed in the previous step, set the final sampling parameter combinations generated using the Sobol sequence, and conduct virtual tests for each combination. Conduct reliability verification for each parameter combination. As shown in the appendix Figure 2 Based on the data collected from the simulation, conduct quantitative analysis from three perspectives: function, efficiency, and safety. The reliability of the AMR working environment is affected by three factors: function, efficiency, and stability. Among them, the function index is affected by the task completion rate, task completion time, and error rate. The efficiency index is affected by throughput, operating cost, equipment utilization rate, and space utilization rate. The stability index is affected by the failure rate, where: Task completion rate: Obtained by the number of tasks successfully completed within a preset time period / the total number of tasks executed within the preset time period. Among them, the total number of tasks is the sum of the number of tasks successfully completed and the number of task failures; Task completion time: The average time taken to successfully complete tasks within a preset time period; Operating cost: Includes the energy consumption of all devices participating in the task scenario. The specific calculation method is: within a preset time period, the power consumption of the devices participating in the task scenario is multiplied by the unit price of electricity to obtain; AMR equipment utilization rate: The life cycle of AMR includes states such as loading, returning, malfunctioning, pausing, and idling. Each state has a different utilization rate for AMR. Set a utilization weight u of 0 to 1 for each state. During the simulation process, the running states of AMR are statistically analyzed to obtain the proportion t of various running states in the running time of AMR, as shown in the following table:

[0037]

[0038] The AMR equipment utilization rate U can be calculated using the formula:

[0039] Among them, i is the number of each running state; Space utilization rate: Obtained by the floor area of the equipment participating in the task scenario / the total building area. By using the digital twin system, the spatial structure of the AMR working environment can be accurately obtained, and the actual utilization space / the total building space can be used to obtain a more accurate space utilization rate from a three-dimensional perspective; Failure frequency index: Within a preset time period, the number of equipment failures / the number of equipment multiplied by the total number of tasks executed within the preset time period; Simply put, assume that the number of devices participating in the task scenario is 5, and within one day, the total number of task scenarios executed is 4. During these four task executions, a total of 7 equipment failures occurred. Then the failure frequency index is: 7 / 5 × 4; For each sub-index, the digital twin model can, based on big data and machine learning technologies, give the weight configuration and standard value of each sub-index according to the usage data of other similar cases; According to the actual production needs, adjust the index weights and standard values for each index. After adjustment, the weight value of each index is l. Divide the experimental observation value by the standard value to perform dimensionless processing on the observation value, and obtain the dimensionless numerical value m of each index: Using the formula:

[0040] The percentage score of the reliability of the AMR working environment under each parameter combination can be obtained; select the parameter combination with the highest reliability score as the optimal parameter combination, and update the parameters of the real AMR and N devices to achieve virtual-real mapping.

[0041] Example 2: Figure 3 It is a system schematic diagram of a device parameter simulation generation device for an AMR task scenario shown in another exemplary embodiment. The device includes: Process determination module 1: used to determine the task process in any AMR task scenario, and determine the devices participating in the task scenario according to the task process. The devices include AMR and other devices; Device relationship acquisition module 2: used to obtain the task dependence between any two devices according to the interaction relationship between the devices participating in the task scenario; obtain the spatial overlap rate between any two devices according to the floor area of the devices participating in the task scenario; obtain the energy exchange rate between any two devices according to the energy type interaction intensity between the devices participating in the task scenario; Coupling strength acquisition module 3: used to obtain the coupling strength between any two devices according to the task dependence, spatial overlap rate, and energy exchange rate between any two devices; Coupling screening module 4: used to select the coupling strength between any device and AMR from the coupling strengths between any two devices, sort the coupling strengths between any device and AMR, and select the N devices with the highest coupling strength with AMR; Parameter generation module 5: used to obtain the historical operation data of AMR and N devices, and generate the final sampling parameter combination of AMR and N devices according to the historical operation data and coupling strength; Simulation operation module 6: used to construct a digital twin model of the AMR working environment. In the digital twin model, set the parameters of the virtual AMR and N virtual devices according to the final sampling parameter combination, and execute the task process in the AMR task scenario in the digital twin model; Parameter screening module 7: used to obtain the reliability score under each parameter combination respectively, and select the parameter combination with the highest reliability score as the optimal parameter combination; Calibration Module 8: Used to set the real AMR and N real devices according to the optimal parameter combination.

[0042] Embodiment 3: This embodiment provides a storage medium storing a computer program, which, when executed by a main controller, implements each step in the above method; It can be understood that the above-mentioned storage medium can be a read-only memory, a magnetic disk or an optical disc, etc.

[0043] It can be understood that the same or similar parts in the above embodiments can be referred to each other, and the content not detailed in some embodiments can be seen in the same or similar content in other embodiments.

[0044] It should be noted that in the description of the present invention, terms such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise stated, the meaning of "plurality" refers to at least two.

[0045] Any process or method description shown in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or more executable instructions for implementing a specific logical function or process, and the scope of the preferred embodiments of the present invention includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in a reverse order according to the involved functions, rather than in the order shown or discussed, which should be understood by those skilled in the technical field of the embodiments of the present invention.

[0046] It should be understood that each part of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following well-known technologies in the art or a combination thereof can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0047] Those of ordinary skill in the technical field of the present invention can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0048] In addition, in each embodiment of the present invention, each functional unit may be integrated into a processing module, may exist physically alone for each unit, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0049] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, or the like.

[0050] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0051] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for simulating and generating device parameters in an AMR task scenario, characterized in that, The method includes: Determine the task process in any AMR task scenario, and determine the devices participating in the task scenario according to the task process. The devices include AMRs and other devices; Obtain the task dependency between any two devices according to the interaction relationship between the devices participating in the task scenario; obtain the spatial overlap rate between any two devices according to the floor area of the devices participating in the task scenario; obtain the energy exchange rate between any two devices according to the energy type interaction intensity between the devices participating in the task scenario; Obtain the coupling strength between any two devices according to the task dependency, spatial overlap rate, and energy exchange rate between any two devices; Select the coupling strength between any device and the AMR among the coupling strengths between any two devices, sort the coupling strengths between any device and the AMR, and select the N devices with the highest coupling strength with the AMR; Obtain the historical operation data of the AMR and the N devices, and generate the final sampling parameter combination of the AMR and the N devices according to the historical operation data and the coupling strength; Construct a digital twin model of the AMR working environment. In the digital twin model, set the parameters of the virtual AMR and the N virtual devices according to the final sampling parameter combination, and execute the task process in the AMR task scenario in the digital twin model; Obtain the reliability scores under each parameter combination respectively, and select the parameter combination with the highest reliability score as the optimal parameter combination; Set the real AMR and the N real devices according to the optimal parameter combination.

2. The method according to claim 1, wherein The generating the final sampling parameter combination of the AMR and the N devices according to the historical operation data and the coupling strength includes: Obtain the initial parameter ranges of the AMR and the N devices according to the historical operation data; Adopt the Sobol sequence parameter generation method to generate the initial sampling parameter combination of the AMR and the N devices within the initial parameter ranges of the AMR and the N devices. The initial sampling parameters of any two devices satisfy the corresponding coupling relationship; Calculate the sensitivity indices of the N devices according to the initial sampling parameters of the N devices, sort the sensitivity indices of the N devices from largest to smallest, take the AMR as the first sampling, and take the sorting of the sensitivity indices of the N devices as the sampling priorities of the N devices; Adopt the Sobol sequence parameter generation method again, and sequentially generate the final sampling parameter combination of the AMR and the N devices within the initial parameter ranges of the AMR and the N devices according to the sampling priorities. The final sampling parameters of any two devices satisfy the corresponding coupling relationship.

3. The method according to claim 2, wherein The calculating the sensitivity indices of the N devices according to the initial sampling parameters of the N devices includes: Set the task metrics for the AMR task scenario, use the task metrics as the system output, obtain the variance caused by any initial sampling parameter alone on the task metrics, and obtain the variance caused by the interaction of any initial sampling parameter with other initial sampling parameters on the task metrics; Obtain the variance of the system output based on the variance caused by any initial sampling parameter alone on the task metrics and the variance caused by the interaction of any initial sampling parameter with other initial sampling parameters on the task metrics; Obtain the sensitivity index of any initial sampling parameter based on the variance caused by any initial sampling parameter alone on the task metrics and the variance of the system output; Use the sensitivity index of the initial sampling parameter as the sensitivity index of the corresponding device.

4. The method according to claim 3, wherein The obtaining of the task dependency between any two devices according to the interaction relationship between the devices participating in the task scenario includes: Obtain the direct interaction times of any two devices participating in the task scenario in the task process, and respectively obtain the action times of any two devices in the task process; obtain the process dependency coefficient according to the direct interaction times of any two devices in the task process and the action times of any two devices in the task process; Set the weight of each resource, and obtain the sharing degree of any two devices for any resource; obtain the resource sharing degree according to the weight of any resource and the sharing degree of any two devices for any resource; Set the attenuation coefficient, and set the ideal time interval for the actions of any two devices, and obtain the actual time interval for the actions of any two devices; obtain the time coupling coefficient according to the attenuation coefficient, the ideal time interval for the actions of any two devices, and the actual time interval; Respectively set the weights of the process dependency coefficient, the resource sharing degree, and the time coupling coefficient; Perform weighted fusion on the process dependency coefficient, the resource sharing degree, and the time coupling coefficient according to the weights of the process dependency coefficient, the resource sharing degree, and the time coupling coefficient to obtain the task dependency between any two devices.

5. The method according to claim 4, wherein The obtaining of the sharing degree of any two devices for any resource includes: Respectively obtain the time when any two devices use the same resource, and respectively obtain the intersection and union of the time when any two devices use the same resource, and divide the intersection of the time when any two devices use the same resource by the union to obtain the sharing degree of any two devices for any resource.

6. The method according to claim 5, wherein The obtaining of the spatial overlap rate between any two devices according to the floor areas of the devices participating in the task scenario includes: Respectively obtain the floor areas of any two devices, obtain the intersection of the floor areas of any two devices according to the floor areas of any two devices, and divide the intersection of the floor areas of any two devices by the smaller floor area of any two devices to obtain the spatial overlap rate between any two devices.

7. The method according to claim 6, wherein Obtaining the energy exchange rate between any two devices according to the energy type interaction intensity between the devices participating in the task scenario includes: Setting the weight of each energy type, obtaining the interaction intensity between any two devices on the same energy type, and obtaining the energy exchange rate between any two devices according to the weight of any energy type and the interaction intensity between any two devices on the same energy type; The obtaining the interaction intensity between any two devices on the same energy type includes: Respectively obtaining the time proportion of any two devices using the same energy type; and respectively obtaining the intersection and union of the time proportions of any two devices using the same energy type, and dividing the intersection of the time proportions of any two devices using the same energy type by the union to obtain the interaction intensity between any two devices on the same energy type.

8. The method according to claim 7, wherein The obtaining the reliability score for each parameter combination includes: Obtaining the total number of times of executing the AMR task scenario within a preset time period for each parameter combination, and the number of times of successfully completing the AMR task scenario within the preset time period, and dividing the number of times of successfully completing the AMR task scenario within the preset time period by the total number of times of executing the AMR task scenario within the preset time period to obtain the task completion rate; the total number of times of executing the AMR task scenario within the preset time period is the number of times of successfully completing the AMR task scenario within the preset time period plus the number of times of failing to complete the AMR task scenario; Obtaining the average time for successfully completing the AMR task scenario within a preset time period for each parameter combination to obtain the task completion time; Obtaining the total power consumption of the devices participating in the task scenario within a preset time period for each parameter combination, and multiplying the total power consumption by the unit price of electricity to obtain the operating cost; Setting the utilization rate weights of the AMR in different operating states, obtaining the time proportion of the AMR in different operating states within a preset time period for each parameter combination, and obtaining the AMR device utilization rate according to the utilization rate weights of the AMR in different operating states and the time proportion; Obtaining the floor area and the total floor area of the devices participating in the task scenario for each parameter combination, and dividing the floor area of the devices participating in the task scenario by the total floor area to obtain the space utilization rate; Obtaining the number of failures of the devices participating in the task scenario for each parameter combination, and obtaining the failure frequency index according to the number of failures of the devices participating in the task scenario; Performing dimensionless processing on the task completion rate, task completion time, operating cost, AMR device utilization rate, space utilization rate, and failure frequency index, and fusing the dimensionless processed indicators according to the preset weight values of each indicator to obtain the reliability score for each parameter combination.

9. An AMR task scenario device parameter simulation generation device, characterized in that, The device includes: A process determination module: used to determine the task process in any AMR task scenario, and determine the devices participating in the task scenario according to the task process, where the devices include AMR and other devices; Device relationship acquisition module: used to obtain the task dependency between any two devices according to the interaction relationship between the devices participating in the task scenario; obtain the spatial overlap rate between any two devices according to the floor area of the devices participating in the task scenario; obtain the energy exchange rate between any two devices according to the energy type interaction intensity between the devices participating in the task scenario; Coupling strength acquisition module: used to obtain the coupling strength between any two devices according to the task dependency, spatial overlap rate and energy exchange rate between any two devices; Coupling screening module: used to select the coupling strength between any device and the AMR among the coupling strengths between any two devices, sort the coupling strength between any device and the AMR, and select the top N devices with the highest coupling strength with the AMR; Parameter generation module: used to obtain the historical operation data of the AMR and the N devices, and generate the final sampling parameter combination of the AMR and the N devices according to the historical operation data and the coupling strength; Simulation operation module: used to build a digital twin model of the AMR working environment. In the digital twin model, set the parameters of the virtual AMR and the N virtual devices according to the final sampling parameter combination, and execute the task process in the AMR task scenario in the digital twin model; Parameter screening module: used to obtain the reliability score under each parameter combination respectively, and select the parameter combination with the highest reliability score as the optimal parameter combination; Calibration module: used to set the real AMR and the N real devices according to the optimal parameter combination.

10. A storage medium, characterized in that, The storage medium stores a computer program, which when executed by the main controller, implements each step in a method for simulating and generating device parameters in an AMR task scenario as described in any one of claims 1-8.

Images