Method for computer-aided ascertainment of one or more operating configurations of a conveyor line system for piece goods

Abstract

The invention relates to a method for computer-aided ascertainment of one or more operating configurations of a conveyor line system (100) for piece goods (P1, P2, …, P7), wherein the conveyor line system (100) comprises a plurality of conveyor line subsections (C1, C2, …, C5) along which the piece goods (P1, P2, …, P7) are transported on respective conveyor means (1, 2, …, 5) of the conveyor line subsections (C1, C2, …, C5), wherein each conveyor line subsection (C1, C2, …, C5) is associated with a speed (v1, v2, …, v5) of the conveyor means (1, 2, …, 5) of the particular conveyor line subsection (C1, C2, …, C5), wherein, in order to ascertain a particular operating configuration: - the speeds (v1, v2, …, v5) of all of the conveyor line subsections (C1, C2, …, C5) are modeled by a set of parameters (PS) such that the speed (v1, v2, …, v5) of a particular conveyor line subsection (C1, C2, …, C5) is described by a time-dependent periodic function (F1, F2, …, FN) comprising one or more parameters (ai, bi, ci, di); and - optimized parameter values (PSopt) for the set of parameters (PS) are determined, as the particular operating configuration, by means of an optimization method (OPT), wherein the optimization method (OPT) is based on an optimization goal of a high quality level (FT) and, as part of the optimization method (OPT), the quality level (FT) is determined repeatedly by means of a physical simulation (SIM) of the conveyor line system (100) or by means of a function.

Description

[0001] Description

[0002] Method for the computer-aided determination of one or more operating configurations of a conveyor system for piece goods

[0003] The invention relates to a method for the computer-aided determination of one or more operating configurations of a conveyor system for piece goods.

[0004] In industrial facilities, such as logistics systems, conveyor systems for piece goods are regularly used. These systems transport piece goods, such as parcels in a parcel distribution system. The conveyor system comprises a variety of conveyor sections with corresponding conveyors on which the piece goods are transported. The speeds of the individual conveyors can be individually adjusted.

[0005] Traditionally, a control system based on expert knowledge is used to set the appropriate speeds for the conveyors in a conveyor system. This control system also takes into account sensor values ​​recorded during current operation. The sensor system can, for example, comprise a plurality of light beams, which detect when piece goods are currently on a specific section of the conveyor.

[0006] Conventional controls for conveyor systems, for example, are designed to transport as many piece goods as possible through the conveyor system in the shortest possible time. Nevertheless, it is not always guaranteed that the conveyor system will operate optimally. This is due, among other things, to the fact that the sensor values ​​recorded during operation often do not allow any conclusions to be drawn about optimal operation of the conveyor system. The object of the invention is to determine one or more operating configurations of a conveyor system for piece goods using a computer-aided method without taking sensor values ​​into account.

[0007] This object is achieved by the method according to claim 1. Further developments of the invention are defined in the dependent claims.

[0008] The method according to the invention serves for the computer-aided determination of one or more operating configurations of a conveyor system for piece goods. The conveyor system comprises a plurality of successive partial conveyor sections, along which the piece goods are transported from an entrance to an exit of the conveyor system on respective conveyor means (such as conveyor belts) of the partial conveyor sections. Each partial conveyor section is assigned an individually adjustable speed at which the conveyor means of the respective partial conveyor section is driven.

[0009] The consecutive conveyor sections do not necessarily have to be directly connected to one another. For example, it is also possible to provide a chute without a conveyor between two adjacent conveyor sections. Such chutes are often used in conveyor systems whose purpose, among other things, is to separate the transported unit loads so that no, or as few as possible, stacks of unit loads occur at the conveyor system's exit.

[0010] In the method according to the invention, the speeds of all partial conveyor sections are modeled using a set of parameters to determine a respective operating configuration. The modeling is designed such that the speed of a respective partial conveyor section is described by a time-dependent periodic function comprising one or more parameters, wherein the parameter(s) belong to the set of parameters. In other words, the set of parameters includes all parameters of the time-dependent periodic functions that model the speeds of the partial conveyor sections.

[0011] According to the invention, optimized parameter values ​​for the set of parameters are determined as the respective operating configuration by means of an optimization method, wherein the optimization method is based on an optimization goal of a high quality measure. Within the scope of the optimization method, the quality measure is repeatedly determined by means of a physical simulation of the conveyor system or by means of a function that models a physical simulation of the conveyor system, as a function of the parameter values ​​of the set of parameters.

[0012] The quality measure is determined in advance to be suitable with regard to the intended purpose of the conveyor system. The determination of an appropriate quality measure is within the scope of expert action. Examples of quality measures are given below. The physical simulation used in the method according to the invention is based on a simulation model or simulation program that was created in advance and with which the conveyor system can be simulated based on physical laws. The creation of an appropriate simulation program for a conveyor system is known per se and is within the scope of expert action. For example, the well-known development environment Unity® can be used to create a suitable simulation program for carrying out appropriate physical simulations of a conveyor system.

[0013] The method according to the invention is based on the finding that the operation of a conveyor system can be very well modeled by periodically varying the speeds of the conveyors on the conveyor sections. Taking into account a quality measure, optimized parameters for corresponding periodic functions are determined in a simple manner using an optimization process without incorporating current sensor values. The conveyor system can then be controlled based on the parameterized periodic functions by adjusting the speeds of the conveyors according to these parameterized periodic functions.

[0014] In a preferred variant of the method according to the invention, the optimization method is initialized with a plurality of value instances of the set of parameters, wherein the value instances each define parameter values ​​for the set of parameters and the parameter values ​​of each value instance are at least partially different from the parameter values ​​of every other value instance from the plurality of value instances. Thus, a plurality of parameterizations for the set of parameters are initially specified. The optimization method then varies the parameter values ​​of the plurality of value instances depending on the optimization objective in order to find a value instance with the highest possible quality measure.

[0015] In a preferred embodiment, the optimization method is a gradient-free optimization method, i.e., an optimization method in which the optimization does not depend on the gradient of a function to be optimized. Any gradient-free optimization method known from the prior art can be used. In a preferred variant, the gradient-free optimization method used is particle swarm optimization. Nevertheless, a known evolutionary optimization method can also be used as the optimization method, such as CMA-ES optimization (CMA-ES = Covariance Matrix Adaptation Evolution Strategy).Instead of a gradient-free optimization method, a further embodiment of the invention uses a gradient-based optimization method, wherein the gradient-based optimization method uses the function that models the physical simulation of the conveyor system to determine the gradient. In this case, this function is designed to be differentiated.

[0016] The function that models the physical simulation of the conveyor system can be derived from the physical simulation in various ways. Preferably, the function is a neural network learned based on training data derived from the physical simulation.

[0017] As already mentioned above, the quality measure taken into account in the optimization process can be selected differently depending on the intended purpose of the conveyor system. In one variant, the quality measure is designed such that the fewer stacks of piece goods leave the exit of the conveyor system in the physical simulation within a predetermined time interval, the higher the quality measure is, with at least two piece goods being arranged one above the other in a stack of piece goods. This quality measure is used in conveyor systems in which piece goods are to be separated.

[0018] In a further variant, the quality measure is designed such that the less often the event occurs in the physical simulation in a predetermined time interval that a piece of goods rotates at least once around its axis during transport along the partial conveyor lines. This quality measure ensures that damage to the transported piece goods is kept to a minimum. This quality measure is preferably also used in a conveyor system for separating piece goods. In a further variant, the quality measure is designed such that the more piece goods leave the exit of the conveyor system in a predetermined time interval in the physical simulation, the higher it is. This quality measure ensures a high throughput of piece goods through the conveyor system.

[0019] The variants of quality measures described above can also be combined if necessary. In other words, a quality measure can also realize several of the functional relationships defined above.

[0020] In a further preferred variant of the method according to the invention, for at least one partial conveyor section and preferably each partial conveyor section, the parameter(s) of the time-dependent periodic function contain(s) the period of the function and / or the amplitude of the function and / or a time offset in the function and / or a speed offset in the function.

[0021] The time-dependent periodic function for the partial conveyor sections can be defined differently depending on the design. In one variant, the time-dependent periodic function is a sine function for at least one partial conveyor section, and preferably for each partial conveyor section.

[0022] Nevertheless, the time-dependent periodic function can also be another type of periodic function, such as a sawtooth function.

[0023] In a further preferred embodiment of the method according to the invention, a number of operating configurations are determined with the aid of a computer, each operating configuration containing a different operating specification for the conveyor system, the operating specification for each partial conveyor system being contained in the time-dependent periodic function, preferably in combination with a further parameter from the set of parameters. In this way, predefined specifications for the operation of the conveyor system can also be taken into account when determining corresponding operating configurations. For example, the operating specification can specify a target value for the number of piece goods that leave the exit of the conveyor system in a predetermined time interval. Nevertheless, the operating specification can also be defined in any other way.

[0024] In a further preferred embodiment of the method according to the invention, the determined operating configuration or the determined operating configurations are stored in a control device of the conveyor system and the conveyor system is operated by means of the control device based on the determined operating configuration or based on one of the determined operating configurations.

[0025] According to the variant just described, a method for operating a conveyor system for piece goods is thus protected, wherein the operating configuration used for the operation or the operating configurations used for the operation are determined by the method according to the invention or one or more of the previously described variants of the method according to the invention.

[0026] The invention further relates to a device for data processing, comprising means for carrying out the method according to the invention or one or more preferred variants of the method according to the invention.

[0027] Furthermore, the invention relates to a computer program product with a program code stored on a machine-readable carrier for carrying out the method according to the invention or one or more preferred variants of the method according to the invention when the program code is executed on a computer. Furthermore, the invention relates to a computer program with a program code for carrying out the method according to the invention or one or more preferred variants of the method according to the invention when the program code is executed on a computer.

[0028] Examples of embodiments of the invention are described in detail below with reference to the attached figures.

[0029] It shows :

[0030] Fig. 1 is a schematic representation of a conveyor system for which an operating configuration can be determined according to an embodiment of the invention;

[0031] Fig. 2 is a diagram illustrating the steps of an embodiment of the method according to the invention; and

[0032] Fig. 3 shows a representation of a time-dependent periodic function whose parameters are determined using an embodiment of the invention.

[0033] Fig. 1 shows a schematic side view of an example of a conveyor system 100, the operating configuration of which can be determined using the embodiment of the method according to the invention described below. The conveyor system is controlled by a control device CO and comprises a total of five partial conveyor sections CI, C2, C3, C4 and C5. Each partial conveyor section comprises a conveying means in the form of a conveyor belt which can be moved at an individually adjustable speed. Specifically, the partial conveyor section CI comprises the conveyor belt 1, which is moved at the speed v1, the partial conveyor section C2 comprises the conveyor belt 2, which is moved at the speed v2, the partial conveyor section C3 comprises the conveyor belt 3, which is moved at the speed v3, the partial conveyor section C4 comprises the conveyor belt 4, which is moved at the speed v4, and the partial conveyor section C5 comprises the conveyor belt 5, which is moved at the speed v5.There is also a chute R between the partial conveyor section Gl and the lower partial conveyor section C2.

[0034] With the conveyor system 100, piece goods in the form of packages are moved in the transport direction T from an entrance IN to an exit OU. As an example, a total of seven piece goods or packages PI to P7 are shown in Fig. 1. The conveyor system is a so-called delaying line, which is often used in logistics systems and has the aim of separating corresponding piece goods so that they arrive at the exit OU individually and are not stacked on top of one another. The separation of the piece goods is effected by the partially inclined partial conveyor lines Gl to C5 and the chute R.

[0035] Packages arrive at the entrance IN of the conveyor system, some of which are stacked on top of one another. As an example, two package stacks are shown in Fig. 1, one of which comprises packages P1 to P3 and is located on conveyor belt 1, while the other package stack comprises packages P4 and P5 and is sliding down chute R. By setting different speeds for the individual conveyor sections G1 to C5, the separation of the packages can be supported by appropriate decelerations or accelerations between the conveyor sections.

[0036] In the embodiment described here, the aim is to set the speeds of the individual conveyor belts so that as few stacks of packages as possible occur at the exit OU of the conveyor system. In contrast to conventional methods, no current measured values ​​from a sensor on the conveyor belt are taken into account when setting the speeds of the conveyor belts. Instead, the time-varying speeds of the individual conveyor belts are determined in advance as the operating configuration and then used in the operation of the conveyor system without recourse to sensors during operation. The previously determined operating configuration is stored in the control device CO so that it is available during operation of the conveyor system. If necessary, the control device CO can also have its own computing means for determining the operating configuration.

[0037] Fig. 2 illustrates the steps carried out in one embodiment of the method according to the invention. These steps are described below generally for a conveyor system comprising N conveyor sections, whose conveyor belts are moved at corresponding speeds vi (i = 1, ..., N). The method can be used for the conveyor system shown in Fig. 1.

[0038] According to step S 1 of Fig. 2, the individual speeds v l z ..., v N The conveyor belts of the respective conveyor sections are modeled by time-dependent periodic functions Fl, ..., FN. This takes advantage of the knowledge that a periodic change in the individual speeds of the conveyor belts causes accelerations and decelerations between the conveyor belts, which lead to the separation of stacked packages.

[0039] Each periodic function Fi of the individual speeds Vi is described in the embodiment described here by the parameter set 0 consisting of four parameters a± , b± , c± and d± . The periodic function is a sine function, whereby the method according to the invention can also be used for any other periodic functions, such as a sawtooth function. Fig. 3 illustrates the

[0040] In this embodiment, a sine function is used to model a corresponding speed vi of a conveyor belt. Time t is plotted along the abscissa of Fig. 3, while the ordinate represents the corresponding speed vi. Mathematically, the speed vi from Fig. 3 can be described as follows:

[0041] (t) = a t * sin(b, * t + c f ) + d t

[0042] The quantity a± represents the amplitude of the sine function, the quantity b± the period of the sine function, the quantity c± a time offset in the sine function, and the quantity d± a velocity offset in the sine function. These quantities are also illustrated again in Fig. 3.

[0043] By modeling the individual velocities vi with the corresponding parameters a±, b±, c±, and d± of a sine function, a total set of parameters is obtained that contains four parameters for each velocity. This set of parameters is denoted by PS in Fig. 2.

[0044] Based on the speeds modeled by the parameter set PS, an optimization OPT is carried out in step S2 in Fig. 2. As part of the optimization, use is made of a physical simulation S IM of the conveyor system. The corresponding computer program that carries out the physical simulation was created in advance. The creation of the computer program is therefore not part of the method according to the invention. The creation of such a computer program for a conveyor system is known per se from the prior art or is within the scope of expert action. For example, the known development environment Unity® can be used for this purpose. The simulation S IM outputs a corresponding quality measure FT (fitness value). The quality measure is set appropriately depending on the technical purpose of the conveyor system and represents an optimization goal for the conveyor system. For the delaying line in Fig.1, the quality measure is defined in such a way that the smaller the number of stacked packages at the exit OU, the higher the quality measure is. This number is determined via the simulation S IM. This quality measure takes into account the intended purpose of the conveyor system, which is to separate the packages. The appropriate definition of the quality measure lies within the scope of professional action. In a modified

[0045] In this embodiment, the quality measure is determined using a function that models the physical simulation above. This function can, for example, be a neural network learned based on training data obtained from the physical simulation.

[0046] Any gradient-free optimization method can be used as the optimization OPT in step S2 of Fig. 2. Gradient-free means that the optimization does not depend on the gradient of a function to be optimized. In a preferred variant, a known particle swarm optimization is used. Alternatively, other known gradient-free optimization methods, such as evolutionary optimization algorithms, can also be used. In a modified variant, a gradient-based method can also be used as the optimization OPT. In this case, the quality measure is determined using the above-mentioned function, which models the physical simulation and is designed as a differentiable function.

[0047] When carrying out step S2 in Fig. 2, the optimization OPT is first initialized with a large number of value instances of the parameter set PS. In other words, a large number of parameterizations of the parameter set PS with different parameter values ​​are initially generated. Each value instance or each parameterization represents a particle of the swarm when using a particle swarm optimization. Subsequently, each parameterization is evaluated using the simulation S IM, i.e. the corresponding conveyor system is simulated based on the respective parameterizations. The result is the corresponding quality measure FT for each parameterization. If necessary, the simulation can also be run several times for each parameterization, in which case the quality measure is the mean of the quality measures across all simulations.

[0048] Using the quality measure FT, the optimization procedure OPT is then used to search for parameterizations that have the highest possible quality measure. This search is carried out iteratively, with the quality measures for suitably modified parameterizations being determined in each iteration step. Since known optimization procedures are used here, a description of these procedures will be omitted. The optimization procedure is then terminated based on a suitable termination criterion. The termination criterion can be, for example, that the globally highest quality measure of all parameterizations does not change significantly after a certain number of optimization steps.

[0049] As a result of step S2, an optimized parameterization PS is finally obtained 0PTin the form of corresponding values ​​for the parameters a± , b± , c± and d± of all speeds vi of the conveyor belts of the conveyor system. The optimized parameterization PS 0PT represents a corresponding operating configuration of the conveyor system, which ensures optimized operation of the system with regard to the quality standard.

[0050] In the case of the conveyor system 100 of Fig. 1, the optimized parameterization PS 0PT stored in the control unit CO. The control unit CO then adjusts the individual speeds of the conveyor belts of the partial conveyor sections based on the time-dependent sine functions with the optimized parameter values.

[0051] In a further development of the method described here, it is also possible to determine several different operating configurations for the corresponding conveyor system. The respective operating configurations are defined for a different operating specification of the conveyor system. The operating specification is included in the modeling of the periodic functions used to describe the speeds of the conveyor belts and is preferably included therein in combination with an additional parameter of the periodic function. As an operating specification, for example, a target value can be defined for the number of piece goods that leave the exit of the conveyor system in a predetermined time interval.

[0052] The following is an example of a function that takes an operating specification into account:

[0053] The variable speed is defined differently for different operating specifications. This variable is multiplied by the further parameter e±, whereby this parameter is taken into account as an additional parameter in the optimization described above. By defining different operating specifications in the form of different values ​​for the variable speed, a number of different operating configurations can be determined based on the method in Fig. 2, which can then be used to control the corresponding conveyor system. The correspondingly determined operating configuration is then selected depending on the current operating specification. The embodiments of the invention described above have a number of advantages. In particular, a method is created for determining one or more operating configurations of a conveyor system which does not require any observations orMeasured values ​​from the current operation of the conveyor system are required. Instead, the corresponding speeds of the conveyor belts of the conveyor system are modeled using time-dependent periodic functions, whose parameters are determined as part of an optimization process combined with a physical simulation. This creates a compact representation of the regulation for controlling the conveyor system based on a few parameters.

[0054] Regardless of the grammatical gender of a particular term, persons with male, female or other gender identity are included.

Claims

Patent claims 1. Method for the computer-aided determination of one or more operating configurations of a conveyor system (100) for piece goods (Pl, P2, P7), wherein the Conveyor line system (100) comprises a plurality of successive partial conveyor lines (Cl, C2, ..., C5), along which the piece goods (Pl, P2, ..., P7) are transported from an inlet (IN) to an outlet (OU) of the conveyor line system (100) on respective conveyor means (1, 2, ..., 5) of the partial conveyor lines (Cl, C2, ..., C5), wherein each partial conveyor line (Cl, C2, ..., C5) is assigned an individually adjustable speed (vl, v2, ..., v5) with which the conveyor means (1, 2, ..., 5) of the respective partial conveyor line (Cl, C2, ..., C5) is driven, wherein for determining a respective operating configuration: the speeds (vl, v2, ..., v5) of all partial conveyor lines (Cl, C2, ..., C5) are modeled by a set of parameters (PS) such that the speed (vl, v2, ..., v5) of a respective Partial conveyor section (Cl, C2, ..., C5) by a time-dependent periodic function (Fl, F2, ..., FN) comprising one or more parameters (a±, b±, c±, d±), wherein the parameter or parameters (a±, b±, Ci, di) belong to the set of parameters (PS); by means of an optimization method (OPT), optimized parameter values (PSopt) for the set of parameters (PS) are determined as the respective operating configuration, wherein the optimization method (OPT) is based on an optimization objective of a high quality factor (FT) and, within the scope of the optimization method (OPT), the quality factor (FT) is repeatedly determined by means of a physical simulation (SIM) of the conveyor line system (100) or by means of a function which models a physical simulation (SIM) of the conveyor line system (100), as a function of parameter values of the set of parameters (PS).

2. Method according to claim 1, characterized in that the optimization method (OPT) is initialized with a plurality of value instances of the set of parameters (PS), wherein the value instances each define parameter values for the set of parameters (PS) and the parameter values of each value instance are at least partially different from the parameter values of every other value instance from the plurality of value instances, wherein the optimization method (OPT) varies the parameter values of the plurality of value instances depending on the optimization objective in order to find a value instance with the highest possible quality measure (FT).

3. Method according to claim 1 or 2, characterized in that the optimization method (OPT) is a gradient-free optimization method, preferably a particle swarm optimization or an evolutionary optimization, in particular a CMA-ES optimization.

4. The method according to claim 1 or 2, characterized in that the optimization method is a gradient-based optimization method, wherein the gradient-based optimization method uses the function which models the physical simulation (SIM) of the conveyor line system (100) for gradient determination.

5. Method according to one of the preceding claims, characterized in that the function which models the physical simulation (SIM) of the conveyor system (100) is a neural network which is learned based on training data originating from the physical simulation (SIM).

6. Method according to one of the preceding claims, characterized in that the quality measure (FT) is designed in such a way that it is higher, the fewer stacks of piece goods (Pl, P2, ..., P7) in the physical simulation (SIM) reach the output (OU) of the conveyor system (100) in a predetermined time interval, wherein in a stack of piece goods (Pl, P2, ..., P7) at least two piece goods are arranged one above the other.

7. Method according to one of the preceding claims, characterized in that the quality measure (FT) is designed such that it is higher the less frequently in the physical simulation (SIM) in a predetermined time interval the event occurs that a piece of goods (Pl, P2, ..., P7) rotates at least once about its axis during transport along the partial conveyor routes (Cl, C2, ..., C5).

8. Method according to one of the preceding claims, characterized in that the quality measure (FT) is designed such that it is higher the more piece goods (Pl, P2, ..., P7) leave the exit (OU) of the conveyor system in the physical simulation (SIM) in a predetermined time interval.

9. Method according to one of the preceding claims, characterized in that for at least one partial conveyor section (C1, C2, ..., C5) the parameter or parameters (a±, b±, c±, d±) of the time-dependent periodic function (Fl, F2, ..., FN) contain the period (b±) of the function (Fl, F2, ..., FN) and / or the amplitude (a±) of the function (Fl, F2, ..., FN) and / or a time offset (c±) in the function (Fl, F2, ..., FN) and / or a speed offset (d±) in the function Fl, F2, ..., FN).

10. Method according to one of the preceding claims, characterized in that for at least one partial conveyor section (C1, C2, ..., C5) the time-dependent periodic function (F1, F2, ..., FN) is a sine function.

11. Method according to one of the preceding claims, characterized in that several operating configurations are determined, each operating configuration having a different operating specification for the conveyor system (100) wherein the operating specification for each partial conveyor section (Cl, C2, ..., C5) is contained in the time-dependent periodic function, preferably in combination with a further parameter of the set of parameters (PS).

12. Method according to one of the preceding claims, characterized in that the operating specification defines a target value for the number of piece goods (P1, P2, ..., P7) which leave the exit (OU) of the conveyor system (100) in a predetermined time interval.

13. Method according to one of the preceding claims, characterized in that the determined operating configuration or the determined operating configurations are stored in a control device (CO) of the conveyor line system (100) and the conveyor line system (100) is operated by means of the control device (CO) based on the determined operating configuration or based on one of the determined operating configurations.

14. A data processing device comprising means for carrying out a method according to one of claims 1 to 13.

15. A computer program product comprising a program code stored on a machine-readable medium for carrying out a method according to one of claims 1 to 13 when the program code is executed on a computer.

16. A computer program comprising a program code for carrying out a method according to any one of claims 1 to 13 when the program code is executed on a computer.

Images