AMR task scenario equipment parameter simulation generation method, device and storage medium

Abstract

The present invention relates to a method, device and storage medium for simulating and generating equipment parameters for AMR task scenarios, which are applied to the field of digital twin technology. The method comprises: determining the task processes of different AMR task scenarios to thereby determine the equipment involved in the task scenarios; obtaining the interaction relationship between any two devices (including AMRs) involved in the task scenarios to thereby determine the coupling relationship between any two devices; screening N devices with strong coupling relationships with the AMRs; generating sampling parameter combinations of the AMRs and the N devices based on the historical operating data of the devices and the coupling relationships; constructing a digital twin model of the AMR task scenario through digital twin technology; simulating the operation of the task processes for different parameter combinations in the digital twin model; obtaining the reliability score corresponding to each parameter combination to thereby screen out the optimal parameter combination; and updating the parameters of the real AMRs and the equipment based on the optimal parameter combination.

Description

Technical Field

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

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

[0003] 3D simulation technology uses three-dimensional software to model and render the AMR working environment and then create animations. For example, the simulation functions provided by software such as Flexsim and Plant Simulation can simulate the operating conditions of the working environment by inputting certain initial data. For example, "Research on Visual Simulation and Optimization of Automated Warehousing and Logistics Systems" provides a solution for 3D visual simulation of automated warehousing and logistics systems, and uses simulation results to evaluate the reliability of the system.

[0004] However, traditional simulation methods rely heavily on experience and industry knowledge when setting parameters, requiring expert experience and on-site investigations before setting them. However, due to the differences between different AMR working environment schemes, parameters set based solely on experience are often not suitable for scenarios and tasks, and cannot guarantee stable performance in multiple simulated schemes, nor can they maximize the efficiency of the AMR working environment, resulting in inaccurate evaluations. In addition, a logistics warehouse is a complex multi-factor system that requires setting a large number of parameters, and there is multi-factor coupling between the parameters. Traditional methods usually set parameters independently one by one, ignoring the connection between the parameters. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide an AMR task scenario equipment parameter simulation generation method, device and storage medium to solve the problem in the prior art that parameter setting relies more on experience and industry knowledge, requires expert experience and on-site investigation, and then sets the parameters. However, due to the differences between different AMR working environment schemes, the parameters set only based on experience are often not suitable for the scene and task. At the same time, it solves the problem that the logistics warehouse is a multi-factor complex system that requires more parameters to be set, and there is multi-factor coupling between the parameters. Traditional methods usually set the parameters one by one independently, ignoring the problem of the connection between the parameters.

[0006] According to a first aspect of an embodiment of the present invention, a method for simulating and generating device parameters for an AMR task scenario is provided, the method comprising:

[0007] Determine the task flow for any AMR task scenario, and determine the devices involved in the task scenario based on the task flow, including AMRs and other devices;

[0008] Obtaining the task dependency between any two devices based on the interaction relationship between the devices participating in the task scenario; obtaining the spatial overlap rate between any two devices based on the floor space occupied by the devices participating in the task scenario; and obtaining the energy exchange rate between any two devices based on the energy type interaction intensity between the devices participating in the task scenario.

[0009] Obtaining the coupling strength between any two devices according to the task dependency, spatial overlap rate, and energy exchange rate between the any two devices;

[0010] Selecting the coupling strength between any device and the AMR from the coupling strength between any two devices, sorting the coupling strengths between any device and the AMR, and selecting N devices with the highest coupling strengths with the AMR;

[0011] Acquire historical operating data of the AMR and N devices, and generate a final sampling parameter combination of the AMR and the N devices according to the historical operating data and coupling strength;

[0012] Constructing a digital twin model of the AMR working environment, setting parameters of the virtual AMR and N virtual devices in the digital twin model according to the final sampling parameter combination, and executing the task flow in the AMR task scenario in the digital twin model;

[0013] Obtain the reliability scores for each parameter combination respectively, and select the parameter combination with the highest reliability score as the optimal parameter combination;

[0014] The real AMR and N real devices are set according to the optimal parameter combination.

[0015] Preferably,

[0016] Generating the AMR and the final sampling parameter combination of N devices according to the historical operation data and the coupling strength includes:

[0017] Obtaining initial parameter ranges for the AMR and N devices based on the historical operation data;

[0018] Using the Sobol sequence parameter generation method, within the initial parameter ranges of the AMR and the N devices, a combination of initial sampling parameters of the AMR and the N devices is generated, and the initial sampling parameters of any two devices satisfy a corresponding coupling relationship;

[0019] Calculate the sensitivity indexes of N devices based on their initial sampling parameters, sort the sensitivity indexes of the N devices from largest to smallest, prioritize AMR for sampling, and use the sensitivity index ranking of the N devices as the sampling priority for the N devices.

[0020] The Sobol sequence parameter generation method is used again to generate the final sampling parameter combination of the AMR and N devices in sequence according to the sampling priority within the initial parameter range of the AMR and N devices. The final sampling parameters of any two devices satisfy the corresponding coupling relationship.

[0021] Preferably,

[0022] Calculating the sensitivity indexes of the N devices according to the initial sampling parameters of the N devices includes:

[0023] Setting a task indicator for an AMR task scenario, taking the task indicator as a system output, obtaining the variance of the task indicator caused by any initial sampling parameter alone, and obtaining the variance of the task indicator caused by the interaction of any initial sampling parameter with other initial sampling parameters;

[0024] Obtaining the variance of the system output according to the variance of the task index caused by the arbitrary initial sampling parameter alone and the variance of the task index caused by the interaction of the arbitrary initial sampling parameter with other initial sampling parameters;

[0025] Obtaining a sensitivity index of any initial sampling parameter based on the variance of the task index caused by the arbitrary initial sampling parameter and the variance of the system output;

[0026] The sensitivity index of the initial sampling parameter is used as the sensitivity index of the corresponding device.

[0027] Preferably,

[0028] The acquiring of the task dependency between any two devices according to the interaction relationship between the devices participating in the task scenario includes:

[0029] Obtaining the number of direct interactions between any two devices participating in the task scenario in the task process, and respectively obtaining the number of actions of any two devices in the task process; obtaining a process dependency coefficient based on the number of direct interactions between any two devices in the task process and the number of actions of any two devices in the task process;

[0030] Set the weight of each resource and obtain the degree of sharing of any resource between any two devices; obtain the resource sharing degree based on the weight of any resource and the degree of sharing of any resource between any two devices;

[0031] Setting an attenuation coefficient and an ideal time interval for the actions of any two devices, and obtaining an actual time interval for the actions of any two devices; obtaining a time coupling coefficient based on the attenuation coefficient, the ideal time interval for the actions of any two devices, and the actual time interval;

[0032] respectively setting weights of the process dependency coefficient, resource sharing degree, and time coupling coefficient;

[0033] According to the weights of the process dependency coefficient, resource sharing degree and time coupling coefficient, the process dependency coefficient, resource sharing degree and time coupling coefficient are weightedly fused to obtain the task dependency between any two devices.

[0034] Preferably,

[0035] The obtaining of the degree of sharing of any resource between any two devices includes:

[0036] The time when any two devices use the same resource is obtained respectively, and the intersection and union of the time when any two devices use the same resource are obtained respectively. The intersection of the time when any two devices use the same resource is divided by the union to obtain the degree of sharing of the arbitrary resource by the arbitrary two devices.

[0037] Preferably,

[0038] The obtaining of the spatial overlap rate between any two devices according to the occupied areas of the devices participating in the task scenario includes:

[0039] The footprints of any two devices are obtained respectively, and the intersection of the footprints of any two devices is obtained based on the footprints of any two devices. The intersection of the footprints of any two devices is divided by the smaller footprint of any two devices to obtain the spatial overlap rate between any two devices.

[0040] Preferably,

[0041] The acquiring 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:

[0042] Set the weight of each energy type, obtain the interaction strength of any two devices on the same energy type, and obtain the energy exchange rate between any two devices based on the weight of any energy type and the interaction strength of any two devices on the same energy type.

[0043] Obtaining the interaction strength of any two devices on the same energy type includes:

[0044] Obtain the time proportions of any two devices using the same energy type respectively; and obtain the intersection and union of the time proportions of any two devices using the same energy type respectively, and divide the intersection of the time proportions of any two devices using the same energy type by the union to obtain the interaction intensity of the any two devices on the same energy type.

[0045] Preferably,

[0046] Obtaining the reliability score for each parameter combination includes:

[0047] Obtain the total number of AMR task scenarios executed within a preset time period under each parameter combination, as well as the number of AMR task scenarios successfully completed within the preset time period. Divide the number of AMR task scenarios successfully completed within the preset time period by the total number of AMR task scenarios executed within the preset time period to obtain the task completion rate. The total number of AMR task scenarios executed within the preset time period is the number of AMR task scenarios successfully completed within the preset time period plus the number of AMR task scenarios failed to complete.

[0048] Obtain the average time to successfully complete the AMR task scenario within the preset time period under each parameter combination to obtain the task completion time;

[0049] Obtain the total power consumption of the devices involved in the task scenario within the preset time period under each parameter combination, and multiply the total power consumption by the unit price of electricity to obtain the operating cost;

[0050] Set the utilization weights of the AMR in different operating states, obtain the time proportions of the AMR in different operating states within the preset time period under each parameter combination, and obtain the AMR equipment utilization based on the utilization weights and time proportions of the AMR in different operating states.

[0051] Obtain the floor space occupied by the equipment involved in the mission scenario and the total building area for each parameter combination. Divide the floor space occupied by the equipment involved in the mission scenario by the total building area to obtain the space utilization rate.

[0052] Obtaining the number of failures of the equipment participating in the task scenario under each parameter combination, and obtaining a failure frequency index according to the number of failures of the equipment participating in the task scenario;

[0053] The task completion rate, task completion time, operating cost, AMR equipment utilization, space utilization, and failure frequency indicators are dimensionally non-valued, and the dimensionally non-valued indicators are fused according to the preset weight values ​​of each indicator to obtain the reliability score under each parameter combination.

[0054] According to a second aspect of an embodiment of the present invention, a device for simulating and generating device parameters for an AMR task scenario is provided, the device comprising:

[0055] Process determination module: used to determine the task process in any AMR task scenario, and determine the devices involved in the task scenario based on the task process, including AMR and other devices;

[0056] Device relationship acquisition module: used to obtain the task dependency between any two devices based on the interaction relationship between the devices participating in the task scenario; obtain the spatial overlap rate between any two devices based on the floor space occupied by the devices participating in the task scenario; and obtain the energy exchange rate between any two devices based on the energy type interaction intensity between the devices participating in the task scenario;

[0057] A coupling strength acquisition module is configured to acquire the coupling strength between any two devices based on the task dependency, spatial overlap rate, and energy exchange rate between the two devices;

[0058] Coupling screening module: used for selecting the coupling strength between any two devices and the coupling strength between them, sorting the coupling strengths between any devices and the AMR, and selecting N devices with the highest coupling strengths with the AMR;

[0059] Parameter generation module: used to obtain historical operation data of the AMR and N devices, and generate the final sampling parameter combination of the AMR and N devices based on the historical operation data and coupling strength;

[0060] A simulation operation module is 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 flow under the AMR task scenario is executed in the digital twin model;

[0061] Parameter screening module: used to obtain the reliability score of each parameter combination and select the parameter combination with the highest reliability score as the optimal parameter combination;

[0062] Calibration module: used to set the real AMR and N real devices according to the optimal parameter combination.

[0063] According to a third aspect of an embodiment of the present invention, a storage medium is provided, wherein the storage medium stores a computer program, and when the computer program is executed by a host controller, each step in the above method is implemented.

[0064] The technical solutions provided by the embodiments of the present invention may have the following beneficial effects:

[0065] This application determines the task flow of different AMR task scenarios to determine the devices involved in the task scenario, obtains the interaction relationship between any two devices (including AMR) involved in the task scenario to determine the coupling relationship between any two devices, and screens N devices with strong coupling relationships with AMR, and generates sampling parameter combinations of AMR and N devices based on the historical operation data of the devices and the coupling relationship; through digital twin technology, a digital twin model of the AMR task scenario is constructed, and in the digital twin model, the task flow is simulated for different parameter combinations, and the reliability score corresponding to each parameter combination is obtained, so as to screen out the optimal parameter combination, and update the parameters of the real AMR and the device 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 parameter generation process, the coupling relationship between parameters is fully considered, avoiding the problem of traditional methods setting each parameter independently and ignoring the intrinsic connection between parameters.

[0066] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0068] Figure 1 This is a flow chart illustrating a method for simulating and generating device parameters for an AMR task scenario according to an exemplary embodiment;

[0069] Figure 2 is a schematic diagram showing the composition of reliability indicators according to another exemplary embodiment;

[0070] Figure 3 is a system schematic diagram of a device for simulating and generating equipment parameters for an AMR task scenario according to another exemplary embodiment;

[0071] In the accompanying drawings: 1-process determination module, 2-equipment 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-correction module. DETAILED DESCRIPTION

[0072] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. In the following description, when referring to the drawings, like numbers in different figures represent like or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present invention, as detailed in the appended claims.

[0073] Example 1

[0074] Figure 1 FIG. 1 is a flow chart showing a method for simulating and generating device parameters for an AMR task scenario according to an exemplary embodiment. Figure 1 As shown, the method includes:

[0075] S1, determining a task flow in any AMR task scenario, and determining the devices involved in the task scenario according to the task flow, the devices including AMR and other devices;

[0076] S2, obtaining the task dependency between any two devices based on the interaction relationship between the devices participating in the task scenario; obtaining the spatial overlap rate between any two devices based on the floor space occupied by the devices participating in the task scenario; and obtaining the energy exchange rate between any two devices based on the energy type interaction intensity between the devices participating in the task scenario;

[0077] S3, obtaining the coupling strength between any two devices according to the task dependency, spatial overlap rate, and energy exchange rate between the any two devices;

[0078] S4: selecting the coupling strength between any two devices and the coupling strength between them, sorting the coupling strengths between any devices and the AMR, and selecting N devices with the highest coupling strengths with the AMR;

[0079] S5, obtaining historical operation data of the AMR and N devices, and generating a final sampling parameter combination of the AMR and the N devices according to the historical operation data and the coupling strength;

[0080] S6, constructing a digital twin model of the AMR working environment, setting parameters of the virtual AMR and N virtual devices in the digital twin model according to the final sampling parameter combination, and executing the task flow in the AMR task scenario in the digital twin model;

[0081] S7, respectively obtain the reliability score of each parameter combination, and select the parameter combination with the highest reliability score as the optimal parameter combination;

[0082] S8, setting the real AMR and N real devices according to the optimal parameter combination;

[0083] It is understandable that the application first needs to determine the task flow of the AMR task scenario. Based on the task flow, the participating devices (including AMR and other devices) can be determined. Then, in order to accurately calculate other parameters, the temporal and spatial constraints, energy interactions, task coupling and other relationships between physical devices need to be converted into a quantifiable mathematical model: a dynamic influence network between devices is constructed, and the matrix elements represent the coupling strength between devices (0-1). To simplify the analysis process, one device corresponds to one main parameter, and the correlation between the parameters can be obtained by analyzing the coupling relationship between the devices.

[0084] The coupling strength between devices is determined by three factors: task dependency, spatial overlap rate, and energy exchange rate. Task dependency is calculated by weighting the process dependency coefficient, resource sharing, and time coupling coefficient. The process dependency coefficient T f Measures the collaboration intensity between devices due to the task process sequence, reflecting the logical dependencies of devices in the task chain. The specific expression formula is as follows:

[0085]

[0086] Where, N ij For equipment i and j Number of direct interactions in the task chain, N i For equipment i The number of actions in the task flow, N j For devices j The number of actions in the task flow;

[0087] Resource sharing degree R s Quantify the intensity of interaction between devices due to shared resources (such as tools, materials, and space), reflecting the degree of competition or collaboration between devices on physical resources. The specific expression formula is as follows:

[0088]

[0089] Where W k is the weight of resource k (set according to scarcity), S ijk For equipment i and j The degree of sharing of resource k; where S ijk It is obtained from the following formula:

[0090]

[0091] Where,U ik It is a device i Using Resources k time, U jk It is a device j Using Resources k time;

[0092] Time coupling coefficient C t Describes the synergy strength between devices due to the timing relationship of operations, reflecting the degree of synchronization or dependence of devices in the time dimension. The specific expression formula is as follows:

[0093]

[0094] Where, Δ t is the actual time interval between any two devices performing actions in the task flow, Δ t The standard is the ideal time interval, that is, the optimal coordination 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 strength. λ is usually taken as 0.5.

[0095] To sum up, we get the task dependency D ij The calculation formula is:

[0096]

[0097] The weight value α =0.5, β =0.3, γ =0.2, can be fine-tuned according to actual conditions;

[0098] Spatial overlap ratio S ij Calculated by the following formula:

[0099]

[0100] Calculated, where S i 、S j Equipment i and equipment j The floor area;

[0101] Energy exchange rate E ij The calculation formula is:

[0102]

[0103] Where W k represents the weight of energy type k (set according to the energy form), E ijk Representation device i With equipment jThe interaction strength on energy type k is expressed as follows:

[0104]

[0105] Where U ik Representation device i The proportion of time using energy type k, U jk Representation device j The proportion of time using energy type k;

[0106] Finally, the task dependency, spatial overlap rate, and energy exchange rate are dimensionlessly processed. The coupling strength between devices is calculated based on the task dependency, spatial overlap rate, and energy exchange rate, and the device interaction relationship adjacency matrix is ​​constructed as follows:

[0107]

[0108] equipment i With equipment j The coupling strength C ij , the calculation formula is:

[0109]

[0110] in α, β, γ The preset values ​​are 0.6, 0.3, and 0.1, which can be fine-tuned as needed. For example, in energy-sensitive scenarios, E can be appropriately increased. ij The weight of

[0111] Based on the device interaction adjacency matrix, the coupling strengths of all devices with the AMR can be obtained. Devices with high coupling strengths with the AMR can be screened by setting a coupling strength threshold. Alternatively, the coupling strengths of all devices with the AMR can be ranked and the top N devices can be selected. In this embodiment, the top N devices ranked by coupling strength are selected.

[0112] Obtain historical operating data of the AMR and the selected N devices. Based on the historical operating data, kernel density estimation can be used to determine the initial parameter ranges of the AMR and the N devices.

[0113] Sobol sequence parameter generation:

[0114] 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 to randomly generated data, its core advantages are: uniform coverage, efficient convergence, and deterministic repeatability. The sample points are evenly distributed to avoid the clustering phenomenon of randomly generated data. Under the same sample size, the integral estimation error is significantly lower than that of random generation. The generated sequence is completely reproducible, which facilitates debugging and verification. Historical correlation is used to ensure that the sampling parameters meet the coupling relationship of the previous step, reducing invalid parameter combinations. Finally, the generated parameter combination also meets the constraints of time and space occupancy, and the rationality of the parameters is improved, thereby improving the quality of parameter generation, that is, generating the initial sampling parameters of the AMR and N devices.

[0115] Sensitivity testing:

[0116] Take the initial sampling parameters of N devices as input and perform variance decomposition as follows:

[0117]

[0118] Where Var(Y) is the variance of output Y, where V i is the parameter X i The variance caused by the single factor, V ij is the parameter X i With X j The variance caused by the interaction; Y is the system indicator, such as task completion time, total energy consumption, accuracy, etc.

[0119] Use the formula:

[0120]

[0121] Calculation parameter X i The proportion of the impact of a single change on the output Y, as a sensitivity index;

[0122] Sort the N devices by their sensitivity indexes. The larger the sensitivity index, the higher the ranking. The sensitivity index ranking of the N devices is used as the sampling priority. It should be emphasized that AMRs do not participate in the sensitivity calculation and are always prioritized.

[0123] After confirming the sampling priority, the Sobol sequence parameter generation method is used again to generate the final sampling parameters of the AMR and N devices in the sampling order, increasing the sampling density within the high-sensitivity range so that the final sampling parameters also meet the coupling relationship of the previous step;

[0124] Digital twin system construction:

[0125] Based on digital twin theory, combined with its composition, structural relationships, application object characteristics, and scenario functional requirements, a digital twin model suitable for device parameter evaluation in AMR mission environments was designed. The model consists of four parts: the physical layer, the data layer, the model layer, and the service layer.

[0126] Use 3D modeling software to build geometric models of the AMR, road surface, equipment, etc. at a 1:1 scale, and assign them appearances such as materials, colors, skins, and textures. Import the models into Unity and render them using Unity's built-in renderer. The process is shown in the figure below:

[0127] 3D model construction:

[0128] 3dsMax is also the current mainstream 3D modeling software. It focuses more on modeling the appearance rather than building complex internal structures. However, the software has very complete rendering capabilities and is widely used in the field of visual monitoring.

[0129] Due to the complexity and large number of equipment 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 three-dimensional model is mainly for the dynamic and static models, and 3dsMax is used to model the AMR and other equipment. The construction of components such as motors, rollers, and bearings is completed first, and then the whole machine is assembled.

[0130] Virtual scene construction:

[0131] Unity3D is a mainstream game engine in the world. With the increasing demand for equipment monitoring, more and more researchers choose Unity3D as visual monitoring software. Based on the appearance data of previous observations, equipment is arranged in a virtual environment in Unity3D. The entire virtual scene consists of multiple parts such as AMR, other equipment, roads, and buildings. The model is arranged according to their actual spatial layout and coordination relationships. The Light effect in Unity3D is added to simulate the lighting effects in the actual scene. The component function provided by the software is used to set auxiliary equipment, floors and other objects to complete the construction of the entire equipment scene and ensure high-fidelity restoration of the equipment. At the same time, in order to prevent movements that do not conform to the actual situation during subsequent system operation, it is necessary to establish a hierarchical dependency relationship for all components in the virtual scene, connect all subcomponents according to the subordinate relationship, and produce a virtual entity that is highly consistent with the physical entity.

[0132] Behavioral model building:

[0133] All real-time data generated by the movement of physical entities are collected and transmitted to the virtual system. After processing the data, the system uses this real-time data to drive the virtual entity to perform corresponding actions, completing the real-time mapping from physical to virtual. The dynamic behavior of the virtual entity is mainly translation, rotation and scaling. By applying the above three transformations, the dynamic behavior of the virtual entity can be realized. The Transform properties in Unity are used to complete a series of translation, rotation and scaling operations on the object. Through the combination of basic movements, the simulation of all AMR running actions is realized, the construction of the behavior model is completed, and the real-time dynamic mapping of physical entities to virtual entities is realized.

[0134] In the virtual environment constructed in the previous step, set the final sampling parameter combination generated by the Sobol sequence, and perform virtual tests on each combination to verify the reliability of each parameter combination, as shown in the attached figure. Figure 2 As shown in the figure, based on the data collected from the simulation, a quantitative analysis is conducted from the perspectives of function, efficiency, and safety:

[0135] The reliability of the AMR working environment is affected by three factors: function, efficiency, and stability. Functional indicators are affected by task completion rate, task completion time, and error rate. Efficiency indicators are affected by throughput, operating costs, equipment utilization, and space utilization. Stability indicators are affected by failure rate.

[0136] Task completion rate:

[0137] The total number of tasks is the number of successfully completed tasks plus the number of failed tasks.

[0138] Task completion time:

[0139] The average time to successfully complete a task within a preset time period;

[0140] Running costs:

[0141] The energy consumption of all devices involved in the task scenario is calculated by multiplying the power consumption of the devices involved in the task scenario by the unit price of electricity within the preset time period.

[0142] AMR equipment utilization rate:

[0143] The life cycle of an AMR includes states such as loading, returning, faulty, paused, and empty. Each state has a different utilization rate for the AMR. A utilization weight u is set for each state between 0 and 1. During the simulation process, the operating states of the AMR are counted to obtain the proportion t of the AMR operating time in each operating state, as shown in the following table:

[0144]

[0145]

[0146] The AMR equipment utilization rate U can be calculated using the following formula:

[0147]

[0148] Wherein, i is the number of each operating state;

[0149] Space utilization:

[0150] The task scenario is obtained by calculating the floor space / total building area of ​​the equipment involved. The digital twin system can accurately obtain the spatial structure of the AMR working environment and use the actual utilized space / total building space to obtain a more accurate space utilization rate from a three-dimensional perspective.

[0151] Fault frequency index:

[0152] The number of device failures during a preset time period is calculated by dividing the number of devices by the total number of tasks executed during the preset time period. For example, if there are 5 devices involved in a task scenario and the total number of task scenarios executed in one day is 4, and there are 7 device failures during these four tasks, then the failure frequency index is 7 / 5×4.

[0153] For each sub-indicator, the digital twin model can provide the weight configuration and standard value of each sub-indicator based on big data and machine learning technology and the usage data of other similar cases;

[0154] According to actual production needs, the weights and standard values ​​of various indicators are adjusted. The weight value of each indicator after adjustment is l. The experimental observation value / standard value is divided and the observation value is dimensionless to obtain the dimensionless value m of each indicator:

[0155] Using the formula:

[0156]

[0157] The reliability of the AMR working environment can be obtained in percentage under each parameter combination. The parameter combination with the highest reliability score is selected as the optimal parameter combination, and the parameters of the real AMR and N devices are updated to achieve virtual-real mapping.

[0158] Example 2:

[0159] Figure 3 2 is a system diagram illustrating an apparatus for simulating and generating device parameters for an AMR task scenario according to another exemplary embodiment, the apparatus comprising:

[0160] Process determination module 1: used to determine the task process in any AMR task scenario, and determine the devices involved in the task scenario based on the task process, including AMRs and other devices;

[0161] Device relationship acquisition module 2: used to acquire the task dependency between any two devices based on the interaction relationship between the devices participating in the task scenario; acquire the spatial overlap rate between any two devices based on the floor space occupied by the devices participating in the task scenario; and acquire the energy exchange rate between any two devices based on the energy type interaction intensity between the devices participating in the task scenario.

[0162] Coupling strength acquisition module 3: used to obtain the coupling strength between any two devices based on the task dependency, spatial overlap rate and energy exchange rate between the any two devices;

[0163] Coupling screening module 4: configured to select the coupling strength between any two devices and the coupling strength between the devices and the AMR, sort the coupling strengths between the devices and the AMR, and select N devices with the highest coupling strengths with the AMR;

[0164] Parameter generation module 5: used to obtain historical operation data of the AMR and N devices, and generate a final sampling parameter combination of the AMR and N devices based on the historical operation data and coupling strength;

[0165] Simulation operation module 6: used to build a digital twin model of the AMR working environment, in which the parameters of the virtual AMR and N virtual devices are set according to the final sampling parameter combination, and the task flow under the AMR task scenario is executed in the digital twin model;

[0166] Parameter screening module 7: used to obtain the reliability score of each parameter combination and select the parameter combination with the highest reliability score as the optimal parameter combination;

[0167] Calibration module 8: configured to set the real AMR and N real devices according to the optimal parameter combination.

[0168] Example 3:

[0169] This embodiment provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a host controller, each step in the above method is implemented;

[0170] It is understandable that the storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0171] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0172] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" is at least two.

[0173] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0174] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0175] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related 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.

[0176] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0177] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0178] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0179] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for simulating and generating device parameters for an AMR task scenario, characterized in that: The method comprises: Determine the task flow for any AMR task scenario, and determine the devices involved in the task scenario based on the task flow, including AMRs and other devices; Obtaining the task dependency between any two devices based on the interaction relationship between the devices participating in the task scenario; obtaining the spatial overlap rate between any two devices based on the floor space occupied by the devices participating in the task scenario; and obtaining the energy exchange rate between any two devices based on the energy type interaction intensity between the devices participating in the task scenario. Obtaining the coupling strength between any two devices according to the task dependency, spatial overlap rate, and energy exchange rate between the any two devices; Selecting the coupling strength between any device and the AMR from the coupling strength between any two devices, sorting the coupling strengths between any device and the AMR, and selecting N devices with the highest coupling strengths with the AMR; Acquire historical operating data of the AMR and N devices, and generate a final sampling parameter combination of the AMR and the N devices according to the historical operating data and coupling strength; Constructing a digital twin model of the AMR working environment, setting parameters of the virtual AMR and N virtual devices in the digital twin model according to the final sampling parameter combination, and executing the task flow in the AMR task scenario in the digital twin model; Obtain the reliability scores for each parameter combination respectively, and select the parameter combination with the highest reliability score as the optimal parameter combination; The real AMR and N real devices are set according to the optimal parameter combination.

2. The method according to claim 1, characterized in that Generating the AMR and the final sampling parameter combination of N devices according to the historical operation data and the coupling strength includes: Obtaining initial parameter ranges for the AMR and N devices based on the historical operation data; Using the Sobol sequence parameter generation method, within the initial parameter ranges of the AMR and the N devices, a combination of initial sampling parameters of the AMR and the N devices is generated, and the initial sampling parameters of any two devices satisfy a corresponding coupling relationship; Calculate the sensitivity indexes of N devices based on their initial sampling parameters, sort the sensitivity indexes of the N devices from largest to smallest, prioritize AMR for sampling, and use the sensitivity index ranking of the N devices as the sampling priority for the N devices. The Sobol sequence parameter generation method is used again to generate the final sampling parameter combination of the AMR and N devices in sequence according to the sampling priority within the initial parameter range of the AMR and N devices. The final sampling parameters of any two devices satisfy the corresponding coupling relationship.

3. The method according to claim 2, characterized in that Calculating the sensitivity indexes of the N devices according to the initial sampling parameters of the N devices includes: Setting a task indicator for an AMR task scenario, taking the task indicator as a system output, obtaining the variance of the task indicator caused by any initial sampling parameter alone, and obtaining the variance of the task indicator caused by the interaction of any initial sampling parameter with other initial sampling parameters; Obtaining the variance of the system output according to the variance of the task index caused by the arbitrary initial sampling parameter alone and the variance of the task index caused by the interaction of the arbitrary initial sampling parameter with other initial sampling parameters; Obtaining a sensitivity index of any initial sampling parameter based on the variance of the task index caused by the arbitrary initial sampling parameter and the variance of the system output; The sensitivity index of the initial sampling parameter is used as the sensitivity index of the corresponding device.

4. The method according to claim 3, characterized in that The acquiring of the task dependency between any two devices according to the interaction relationship between the devices participating in the task scenario includes: Obtaining the number of direct interactions between any two devices participating in the task scenario in the task process, and respectively obtaining the number of actions of any two devices in the task process; obtaining a process dependency coefficient based on the number of direct interactions between any two devices in the task process and the number of actions of any two devices in the task process; Set the weight of each resource and obtain the degree of sharing of any resource between any two devices; obtain the resource sharing degree based on the weight of any resource and the degree of sharing of any resource between any two devices; Setting an attenuation coefficient and an ideal time interval for the actions of any two devices, and obtaining an actual time interval for the actions of any two devices; obtaining a time coupling coefficient based on the attenuation coefficient, the ideal time interval for the actions of any two devices, and the actual time interval; respectively setting weights of the process dependency coefficient, resource sharing degree, and time coupling coefficient; According to the weights of the process dependency coefficient, resource sharing degree and time coupling coefficient, the process dependency coefficient, resource sharing degree and time coupling coefficient are weightedly fused to obtain the task dependency between any two devices.

5. The method according to claim 4, characterized in that The obtaining of the degree of sharing of any resource between any two devices includes: The time when any two devices use the same resource is obtained respectively, and the intersection and union of the time when any two devices use the same resource are obtained respectively. The intersection of the time when any two devices use the same resource is divided by the union to obtain the degree of sharing of the arbitrary resource by the arbitrary two devices.

6. The method according to claim 5, characterized in that The obtaining of the spatial overlap rate between any two devices according to the occupied areas of the devices participating in the task scenario includes: The footprints of any two devices are obtained respectively, and the intersection of the footprints of any two devices is obtained based on the footprints of any two devices. The intersection of the footprints of any two devices is divided by the smaller footprint of any two devices to obtain the spatial overlap rate between any two devices.

7. The method according to claim 6, characterized in that The acquiring 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: Set the weight of each energy type, obtain the interaction strength of any two devices on the same energy type, and obtain the energy exchange rate between any two devices based on the weight of any energy type and the interaction strength of any two devices on the same energy type. Obtaining the interaction strength of any two devices on the same energy type includes: Obtain the time proportions of any two devices using the same energy type respectively; and obtain the intersection and union of the time proportions of any two devices using the same energy type respectively, and divide the intersection of the time proportions of any two devices using the same energy type by the union to obtain the interaction intensity of the any two devices on the same energy type.

8. The method according to claim 7, characterized in that Obtaining the reliability score for each parameter combination includes: Obtain the total number of AMR task scenarios executed within a preset time period under each parameter combination, as well as the number of AMR task scenarios successfully completed within the preset time period. Divide the number of AMR task scenarios successfully completed within the preset time period by the total number of AMR task scenarios executed within the preset time period to obtain the task completion rate. The total number of AMR task scenarios executed within the preset time period is the number of AMR task scenarios successfully completed within the preset time period plus the number of AMR task scenarios failed to complete. Obtain the average time to successfully complete the AMR task scenario within the preset time period under each parameter combination to obtain the task completion time; Obtain the total power consumption of the devices involved in the task scenario within the preset time period under each parameter combination, and multiply the total power consumption by the unit price of electricity to obtain the operating cost; Set the utilization weights of the AMR in different operating states, obtain the time proportions of the AMR in different operating states within the preset time period under each parameter combination, and obtain the AMR equipment utilization based on the utilization weights and time proportions of the AMR in different operating states. Obtain the floor space occupied by the equipment involved in the mission scenario and the total building area for each parameter combination. Divide the floor space occupied by the equipment involved in the mission scenario by the total building area to obtain the space utilization rate. Obtaining the number of failures of the equipment participating in the task scenario under each parameter combination, and obtaining a failure frequency index according to the number of failures of the equipment participating in the task scenario; The task completion rate, task completion time, operating cost, AMR equipment utilization, space utilization, and failure frequency indicators are dimensionally non-valued, and the dimensionally non-valued indicators are fused according to the preset weight values ​​of each indicator to obtain the reliability score under each parameter combination.

9. A device for simulating and generating equipment parameters for an AMR task scenario, characterized in that: The device comprises: Process determination module: used to determine the task process in any AMR task scenario, and determine the devices involved in the task scenario based on the task process, including AMR and other devices; Device relationship acquisition module: used to obtain the task dependency between any two devices based on the interaction relationship between the devices participating in the task scenario; obtain the spatial overlap rate between any two devices based on the floor space occupied by the devices participating in the task scenario; and obtain the energy exchange rate between any two devices based on the energy type interaction intensity between the devices participating in the task scenario; A coupling strength acquisition module is configured to acquire the coupling strength between any two devices based on the task dependency, spatial overlap rate, and energy exchange rate between the two devices; Coupling screening module: used for selecting the coupling strength between any two devices and the coupling strength between them, sorting the coupling strengths between any devices and the AMR, and selecting N devices with the highest coupling strengths with the AMR; Parameter generation module: used to obtain historical operation data of the AMR and N devices, and generate the final sampling parameter combination of the AMR and N devices based on the historical operation data and coupling strength; A simulation operation module is 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 flow under the AMR task scenario is executed in the digital twin model; Parameter screening module: used to obtain the reliability score of each parameter combination 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.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the main controller, it implements the various steps in the AMR task scenario device parameter simulation generation method as described in any one of claims 1 to 8.

Images