Method for providing a metering device for bulk goods, method for obtaining a recommendation for a configuration of a metering device for bulk goods, and devices for processing data

Abstract

The invention relates to a method for ascertaining at least one configuration of a metering device for bulk goods to be metered, to a method for obtaining a recommendation for a configuration of a metering device for bulk goods to be metered, and to devices for processing data.

Description

[0001] Description

[0002] Title of the invention

[0003] Method for providing a dosing device for a bulk material, method for obtaining a recommendation for a configuration of a dosing device for a bulk material and devices for data processing

[0004] field of technology

[0005] The present invention relates to a method for providing a dosing device for a bulk material to be dosed, a method for obtaining a recommendation for a configuration of a dosing device for a bulk material to be dosed, and devices for data processing.

[0006] State of the art

[0007] Dosing devices for dosing bulk materials consist of a multitude of components that must be suitably selected and coordinated depending on the specific bulk material to be dosed. To design a dosing device, it was previously often necessary to examine the physical properties of the bulk material to be dosed in the laboratory and to test its interaction with various designs of mechanical components and with different operating parameter settings in experimental setups. However, reproducible and therefore reliable results from such investigations are only possible with time-consuming and costly measures that also require the deployment of specially trained personnel.

[0008] Summary of the invention

[0009] It is therefore an object of the present invention to overcome the described disadvantages of the prior art and in particular to provide means with which, against the background of a bulk material to be dosed, a configuration of a dosing device suitable for dosing the respective bulk material can be obtained in a simple and yet reliable manner.

[0010] The object is achieved according to a first aspect by a method according to patent claim 1.

[0011] Configuration refers, on the one hand, to the selection of a dosing device suitable for the material to be dosed, and, on the other hand, to the selection or adjustment of the dosing device's operating parameters and components. Often, the first step is to decide which type of dosing device, particularly with regard to the conveying devices used, is suitable for the relevant bulk material. Pneumatic dosing devices (dilute phase conveying, dense phase conveying, etc.) and mechanical dosing devices with various discharge devices such as belt conveyors, screw conveyors, cellular wheels, etc. are available.According to the method according to the invention, in order to determine a configuration of a dosing device for a bulk material to be dosed, a first image of a sample of the bulk material is created and, based on the data of the first image, a type of dosing device and / or a corresponding configuration of the dosing device for the bulk material is determined.

[0012] The invention is therefore based on the surprising discovery that, by taking a sample of a bulk material to be dosed, information about the respective bulk material can be derived that at least implicitly relates to one or more properties of the bulk material that have or have an influence on the dosing behavior of the bulk material. Based on this information, the appropriate dosing device and / or components and / or operating parameters of a dosing device suitable for dosing the respective bulk material can then be determined and output as the configuration of a dosing device.

[0013] This eliminates or at least reduces the need for complex physical property tests on bulk materials. This allows for a particularly quick determination of a suitable configuration for a dosing device based on the bulk material to be dosed.

[0014] In this context, it has been particularly surprising that the configuration suggestion obtained using the proposed method can sometimes be superior to that of an expert. Apparently, the dosing behavior of the bulk material can sometimes be described even better with the information obtained from the recordings than with conventional parameters, which have previously been determined through complex sample tests on complex test rigs, for example, regarding physical parameters of the bulk material.

[0015] The process also makes it particularly advantageous to operate an existing dosing device alternately with different bulk materials without great effort. No material-specific background knowledge is required to determine the configurations. This can increase the utilization of the dosing device and thus its cost-effectiveness, as well as its operational reliability.

[0016] Above all, the proposed method enables even a non-technical person to determine a suitable configuration of a dosing device for a bulk material to be dosed. They can then, for example, select the dosing device itself, components of a dosing device, and / or replace components of an existing dosing device based on a corresponding suggestion. Advantageously, the configuration of a dosing device can be fully or partially automated using the method, particularly with regard to setting operating parameters.

[0017] The proposed method can also be easily applied to existing dosing devices, for example, whose configuration needs to be adjusted or checked against the background of a bulk material to be dosed. It is essentially sufficient to have the bulk material sample available and to evaluate it appropriately. This allows the method to be used with a wide variety of different dosing devices and is extremely flexible.

[0018] Examples of advantageous bulk materials are rock, building materials, in particular topsoil, sand, gravel and / or cement, raw materials, in particular ore, coal, clay and / or road salt, foodstuffs, in particular grain, sugar, salt, coffee and / or flour, and / or powdered goods, in particular pigments, fillers, granules and / or pellets.

[0019] The type of bulk material can be, for example, one of the following bulk material types: dust, powder, flour, grains, granules, shot, lumps, pellets and / or other.

[0020] The method is advantageously computer-implemented. The method can advantageously be provided as a cloud service. Thus, no extensive data processing is required at the location of the dosing device being configured.

[0021] Obtaining a recording advantageously comprises obtaining data, in particular image data, of the recording. For example, the data represents pixel values ​​of the recording. This data can be received in raw format, in a preprocessed image format, and / or from a suitable light-sensitive sensor.

[0022] When the present application refers to a configuration of a dosing device for a bulk material to be dosed, this preferably means the specification of a type designation and / or a unique identifier of at least one component, in particular a mechanical component, to be selected for the dosing device and / or at least one setting for an operating parameter of the dosing device.

[0023] When, in the present application, the configuration is determined "based on" certain data, this advantageously means that the configuration could not be determined without these certain data. These certain data (which may be referred to as initial data) can advantageously be subjected to one or more data processing steps to obtain processed data. Within these data processing steps, the certain data can, for example, be evaluated, further processed, and / or merged with other data. With the help of the certain data, further information, in particular from other sources such as databases, can also be obtained and, for example, be available as intermediate results.Within data processing steps, the additional information may be subjected to further data processing steps alongside or instead of the certain data and / or processed data, including processing with other certain data. More generally, the latter means that several different certain data items may be present "from" which the configuration is determined. Each of these items can be processed individually. At a specific processing step, two or more such different initial data items, possibly already in processed form, are combined and optionally used as input data for subsequent data processing.

[0024] Alternatively or additionally, it can also be provided that the method comprises that the configuration of a dosing device for the bulk material is determined by means of a suggestion module, that the data of the first recording are included in the determination of the configuration by means of the suggestion module and / or that, by means of a first evaluation module, a first property of the bulk material and / or an identifier of the bulk material is determined based on the data of the first recording, and wherein the first bulk material property and / or the identifier is included in the determination of the configuration by means of the suggestion module.

[0025] The identifier can, for example, be a unique identifier (such as an alphanumeric character string, a name, or chemical formula) of the bulk material. Advantageously, using the identifier and incorporating a database, further information, such as pre-stored information, can be determined about the bulk material represented by the identifier. Information about the bulk material, such as material specifications, can then be retrieved from a database using the identifier. This will be discussed in more detail below.

[0026] Preferably, a plurality of first bulk material properties are determined and optionally included in the configuration determination. In one embodiment, the (at least one) first bulk material property is determined using image processing and analysis methods based on the first image. The suggestion module can be implemented, for example, in software, in hardware, or a combination of both. The suggestion module can alternatively or additionally comprise a memory, a processor, a receiving device (for example, to receive the image via this), a transmitting device (for example, to send a generated signal to another entity), or any combination thereof. The suggestion module can alternatively or additionally provide and / or make available and / or comprise everything it comprises, such as, in particular, all resources necessary for this purpose, for example in the form of software and / or hardware resources.

[0027] The first evaluation module can be implemented, for example, in software, hardware, or a combination of both. Alternatively or additionally, the first evaluation module can comprise a memory, a processor, a receiving device (for example, to receive the recording), a transmitting device (for example, to send a generated signal to another entity), or any combination thereof. Alternatively or additionally, the first evaluation module can provide and / or make available and / or comprise everything it comprises, such as, in particular, all the resources necessary for this purpose, for example, in the form of software and / or hardware resources.

[0028] In an advantageous embodiment, the suggestion module comprises the first evaluation module. The first evaluation module and the suggestion module can preferably be identical and thus form a common module.

[0029] In one embodiment, the two modules are operated spatially separated from each other. This is advantageous if the two modules have different requirements for hardware and / or software resources, allowing the module with more computationally intensive operations to be operated in an environment with sufficient hardware and / or software resources. In this case, the modules can exchange data with each other, for example, via a data connection.

[0030] In one embodiment, the data of the first recording represent the first bulk material property and / or the configuration of the dosing device represents the output data of the suggestion module. Further input and / or output data, in particular those described elsewhere in the application, are possible.

[0031] Preferably, the output data of a module are obtained by the respective module at least in part by processing at least the input data of the respective module, i.e. evaluating, analyzing and / or converting them into new data.

[0032] Alternatively or additionally, it can also be provided that the method comprises that, starting from the identifier, information, in particular comprising a first bulk material property, relating to a bulk material assigned to the identifier is retrieved from a database and included in the determination of the configuration by means of the suggestion module.

[0033] The additional information allows for even more reliable and accurate configuration determination. This allows for the inclusion of information about the bulk material that cannot be directly derived from the recorded data but can be obtained from other sources (such as the database). The identifier can be used as a link (relation) for this purpose. This allows the information to be obtained from the recorded data and with the further use of other resources (such as databases, etc.).

[0034] The retrieved information can, for example, be or have a property of the bulk material, such as a first bulk material property. The information is advantageously obtained using the identifier, for example, retrieved from the database.

[0035] Thus, in one embodiment, additional information about the bulk material (in particular based on the identifier from a database) can be determined and included in the determination of the configuration (in particular at least partially by means of the suggestion module).

[0036] Preferably, the information relates to the material properties of the bulk material. Based on the material properties, the suitability of the bulk material for use in a dosing device with specific equipment, for example, with regard to mechanical components and / or the setting of operating parameters, can be advantageously assessed. Therefore, it is advantageous to obtain one or more material properties based on the data from the first recording and with the help of the identifier and to include them in determining the configuration.

[0037] The retrieved information can advantageously be provided to an entity and / or to a user, for example, on a user interface such as a screen. This allows, for example, not only the configuration but also a justification for the circumstances under which the proposed configuration was implemented.

[0038] In one embodiment, alternatively or additionally, at least the retrieved information represents input data of the proposal module. Further input and / or output data, in particular those described elsewhere in the application, are possible.

[0039] Alternatively or additionally, it can also be provided that the method comprises obtaining a data set which represents a second property of the bulk material, wherein (i) based on the data set obtained, a configuration of a dosing device for the bulk material is determined by means of the suggestion module and / or (ii) the data set is included in the determination of the configuration by means of the suggestion module.

[0040] The obtained data set is used in addition to the data from the first image to determine the configuration. The data from the first image and the data set can be processed together to obtain a common intermediate value, which is then further processed to determine the configuration. Alternatively, a first intermediate value is obtained from the image data and a second intermediate value is obtained from the data set, and the first and second intermediate values ​​are further processed to determine the configuration.

[0041] The data set can, for example, represent and / or encode one or more properties of the bulk material. Alternatively or additionally, the data set could also represent a preferably binary character sequence, with each position representing a property of the bulk material. An example of such a character sequence is the binary sequence 0101011101, where, in this sequence, the presence ("1") or absence ("0") of the respective property for the bulk material is encoded for ten bulk material properties (e.g., "sticky," "electrostatic," "granular," etc.).

[0042] In one embodiment, alternatively or additionally, the received data set represents input data of the proposal module. Further input and / or output data described elsewhere in the application are possible.

[0043] Alternatively or additionally, it may also be provided that the data volume is obtained by user input, in particular via a human-machine interface.

[0044] Alternatively or additionally, it can also be provided that the method comprises obtaining a second image of the sample of the bulk material, and wherein (i) based on the data of the second image, the configuration of a dosing device for the bulk material is determined by means of the suggestion module and / or (ii) the data of the second image are included in the determination of the configuration by means of the suggestion module, wherein preferably (i) by means of the first evaluation module, the one first property of the bulk material and / or the one identifier of the bulk material is determined based on the data of the first and second images, and / or (ii) by means of a second evaluation module, a second property of the bulk material is determined based on the data of the first and / or second images and is included in the determination of the configuration by means of the suggestion module.

[0045] The data from the second recording can therefore be used in addition to the data from the first recording (and, if applicable, the amount of data obtained) to determine the configuration.

[0046] Preferably, the data from the first recording is not used to determine the second property. For example, the second property can then be determined based on the data from the second recording by feeding the data from the second recording but not the data from the first recording to the data input of the respective evaluation module. Preferably, additional input data can be provided, which are not the data from the first recording.

[0047] It is also advantageously possible to determine the first bulk material property and / or the second bulk material property using the data from the first and second recordings. For this purpose, the data from the first and second recordings can be fed to the data input of the respective evaluation module. Preferably, additional input data can be provided.

[0048] The first and / or second property determined here is advantageously a different property than the property explained above, represented by the amount of data obtained.

[0049] The second evaluation module can be implemented, for example, in software, hardware, or a combination of both. Alternatively or additionally, the second evaluation module can comprise a memory, a processor, a receiving device (for example, to receive the recording), a transmitting device (for example, to send a generated signal to another entity), or any combination thereof. Alternatively or additionally, the second evaluation module can provide and / or make available and / or comprise everything it comprises, such as, in particular, all the resources necessary for this purpose, for example, in the form of software and / or hardware resources.

[0050] In an advantageous embodiment, the suggestion module comprises the second evaluation module. The second evaluation module and the suggestion module can preferably be identical and thus form a common module.

[0051] In one embodiment, the two modules are operated spatially separated from each other. This is advantageous if the two modules have different requirements for hardware and / or software resources, allowing the module with more computationally intensive operations to be operated in an environment with sufficient hardware and / or software resources. In this case, the modules can exchange data with each other, for example, via a data connection.

[0052] It is also possible that the first evaluation module, the second evaluation module and the suggestion module are identical and / or that the first evaluation module and the second evaluation module are identical.

[0053] In one embodiment, at least the data from the second recording represents input data of the first evaluation module. Further input and / or output data, in particular those described elsewhere in the application, are possible. In one embodiment, alternatively or additionally, at least the data from the first and / or second recording represents input data and / or the second property represents output data of the second evaluation module. Further input and / or output data, in particular those described elsewhere in the application, are possible.

[0054] In one embodiment, alternatively or additionally, the data of the second recording and / or the second property represent input data of the suggestion module. Further input and / or output data, in particular those described elsewhere in the application, are possible.

[0055] Alternatively or additionally, it can also be provided that (i) the first recording and the second recording are carried out, preferably simultaneously or sequentially, from different perspectives and / or (ii) the bulk material sample is in a first sample configuration during the first recording and the bulk material sample is in a second sample configuration during the second recording, wherein the bulk material sample is transferred from the first sample configuration to the second sample configuration between the two recordings.

[0056] For example, the first and second images can be taken with one and the same recording device and the position and / or orientation of the recording device can be changed between the images in order to record the two images one after the other from different perspectives.

[0057] For example, the first and second images can be captured using different recording devices, with the recording devices having different positions and / or orientations. The two images can thus be captured simultaneously from different perspectives, particularly advantageously.

[0058] In one embodiment, the perspectives of the two shots are identical.

[0059] A sample configuration is preferably understood to mean the type and manner of a spatial arrangement of the bulk material of the sample, in particular under existing boundary conditions, such as existing environmental conditions, and / or the conditions of the formation of material accumulations (e.g. clumping) within the arrangement.

[0060] For example, a bulk material sample can be piled onto a flat support from a feed pipe at a certain height. The way in which the bulk material sample forms a pile can then be understood as a sample configuration. This sample configuration can differ from a different sample configuration obtained if the bulk material sample is piled onto the flat support from a different height. Instead of the height, the angle of inclination of the support could also be changed.

[0061] Alternatively or additionally, it can also be provided that the first and second sample configurations are two differently formed heaps of the bulk material sample and / or at least one parameter of the ambient conditions, such as ambient temperature, air humidity and / or ambient pressure, of the bulk material sample is changed between the first and second sample configuration.

[0062] Preferably, the bulk material in both sample configurations is in a state of equilibrium with the respective existing physical environmental conditions.

[0063] For example, a heap can be formed from the sample at two different ambient temperatures (preferably using the same procedure in each case). The different formation of the heap in the two cases represents the different sample configurations. The bulk material of the sample is at the respective ambient temperature, thus in an equilibrium state.

[0064] Another possible environmental condition is the inclination of the base (also mentioned above) on which the bulk material sample is piled up.

[0065] Alternatively or additionally, it can also be provided that the method comprises evaluating and / or analyzing the data of the first and / or second recording using methods of digital image analysis in the field of machine learning, in particular in order to determine the first property, the second property, the identifier and / or the configuration.

[0066] Advantageously, digital image analysis is performed using machine learning methods. For this purpose, a machine learning model can be trained on training data that is of the type of input data expected later, each with associated expected output data. Using the trained model, output data can be calculated from the respective input data, representing the respective specific information or other information.

[0067] Therefore, the suggestion module can execute corresponding methods, in particular on at least the data of the first and / or second recording, in order to determine the configuration.

[0068] Therefore, the first evaluation module can execute corresponding methods on the data of the first and / or second recording in order to determine, for example, the first property of the bulk material, the second property of the bulk material and / or the identifier.

[0069] Therefore, for example, the second evaluation module can execute corresponding methods on the data of the first and / or second recording in order to determine the first and / or second property of the bulk material.

[0070] Alternatively or additionally, it can also be provided that the method comprises obtaining a dosing parameter and, based on the dosing parameter, determining a configuration of a dosing device for the bulk material by means of the suggestion module.

[0071] The dosing parameter is used in addition to the data from the first recording (and, if applicable, the amount of data obtained and / or the data from the second recording) to determine the configuration.

[0072] For example, a maximum speed and / or a minimum dimension of the dosing device's discharge element may be specified for a specific bulk material (especially the bulk material to be dosed). Therefore, the configuration can be determined based on the corresponding restrictions, so that configurations that have higher speeds and / or a discharge element that does not meet the minimum dimensions are not determined.

[0073] The dosing parameter can, for example, represent a characteristic parameter of the dosing device. Examples of this include target, actual, maximum, and / or minimum values ​​of an operating variable. When determining the configuration, the performance of the dosing device can therefore advantageously be taken into account. For example, the configuration can be determined against the background of a specific bulk material (which can be represented by the identifier discussed above) and by including the dosing parameter.

[0074] In one embodiment, alternatively or additionally, at least the dosing parameter represents input data of the suggestion module. Further input and / or output data, in particular those described elsewhere in the application, are possible. Alternatively or additionally, it can also be provided that a control signal representing the determined configuration is generated and fed to an entity as a configuration recommendation and / or output to a user on a human-machine interface, such as a screen, and / or that a dosing device is configured based on the determined configuration.

[0075] The control signal advantageously makes it possible to provide an entity with information about the determined configuration. For example, the entity can be a higher-level dosing device monitoring system and / or a dosing device management system. Alternatively or additionally, the control signal can be supplied to the entity to initiate monitoring of the dosing device and / or for documentation purposes. In this way, a configuration can advantageously be continuously maintained even during ongoing operation of the dosing device—particularly against the background of the bulk material and / or changing operating parameters—and can be optionally updated or compared with the current configuration.

[0076] The entity can be the dosing device for which the configuration is determined, or parts thereof, such as a motor or its motor controller. The entity can also be a device other than the dosing device, for example.

[0077] In one embodiment, the control signal can be an analog or digital signal. Alternatively or additionally, the control signal can also be a command within a software application.

[0078] Alternatively or additionally, it can also be provided that configurations and status data of dosing devices and / or bulk material data for the bulk materials dosed with the dosing devices are received from a cloud-based computer and taken into account in the proposal module when determining the configuration, whereby a provisionally determined configuration is validated on the basis of the received configurations, status data and / or bulk material data and, if the provisionally determined configuration does not correspond to a defined quality standard, is adjusted.

[0079] In this way, information about the configuration, status data, and bulk materials dosed with dosing devices in productive use can be obtained and advantageously used as feedback information when determining the configuration. In this way, the information from productive use can be advantageously incorporated into the configuration decision. Preferably, a data set containing configuration, status data, and bulk material data is obtained for each pairing of dosing devices and the respective bulk material dosed with them.

[0080] If, for example, in a particular configuration the dosing process of a particular bulk material frequently (for example in more than 10%, more than 30%, more than 50% or more than 70% of cases) leads to a status code representing an impairment of the operation of the respective dosing device, such a combination of configuration and bulk material can be avoided and no longer be determined as a configuration in the process.

[0081] Another particularly advantageous feature is the ability to use feedback information to review a determined configuration. For example, a dosing device configuration can initially be determined as a provisional configuration for a bulk material, and this determined provisional configuration is then reviewed using the feedback information received. If it is then determined that the combination of provisional configuration and bulk material frequently (for example, in more than 10%, more than 30%, more than 50%, or more than 70% of cases) leads to a status code representing an impairment of the dosing device's operation, the provisional configuration can advantageously be adjusted and this adjusted configuration can be determined as the configuration, or, optionally, a new provisional configuration can be determined.

[0082] Alternatively or additionally, it can also be provided that the determined configuration is compared with a current configuration of a dosing device used for dosing the bulk material and, depending on the result of the comparison, a control signal is generated which is fed as a control and / or regulating signal to the dosing device and / or to an entity different from the dosing device.

[0083] In this way, the operation of a dosing device can be made more reliable and safer, as the determined configuration can be used to monitor the dosing device and its dosing process. If the determined configuration for the dosing device deviates from the current configuration of the dosing device, a corresponding control signal can be generated.

[0084] The method is therefore particularly suitable for monitoring the use of bulk material during a dosing process of a dosing device. The configuration determined based on the bulk material to be dosed can be compared with the current configuration of the dosing device. Optionally, if deviations are detected that are incompatible with a defined or definable quality parameter, an alarm signal can be generated. In this way, bulk material to be dosed that is not suitable for dosing with the dosing device in its current configuration can be identified. Based on the alarm signal, operating and / or supervisory personnel can be notified and optionally prompted to take action and / or an ongoing dosing process can be aborted.

[0085] This also advantageously makes it possible to continuously monitor the bulk material fed into a dosing device and to propose a new configuration for the respective dosing device and / or abort an ongoing dosing process if the properties of the bulk material have changed and the existing configuration of the dosing device therefore no longer meets defined quality criteria. This method can thus further improve the safety and reliability of the dosing process.

[0086] Above all, this increase in safety essentially requires no structural changes to the dosing device in question. Ultimately, it is sufficient to at least maintain the bulk material intake. This allows the process to be used with a wide variety of dosing devices, including existing ones, and is extremely flexible.

[0087] By monitoring the bulk material being dosed in this way, incorrect filling of a dosing device can be prevented or detected early. Critical situations, including production downtime, can be avoided more reliably than before. Dosing processes that are unmanned and / or remotely controlled can also be monitored better and more reliably, thus avoiding or at least limiting costly production errors.

[0088] The method also makes it particularly advantageous to operate an existing dosing device safely and reliably, alternating with different bulk materials, without great effort. For example, one embodiment can provide for automatic reconfiguration of the dosing device based on the determined configuration. This increases the utilization of the dosing device and thus its cost-effectiveness, and can also enhance operational reliability. Furthermore, the corresponding monitoring of a dosing device can be fully or partially automated using the method, thus further reducing or completely eliminating the susceptibility to errors otherwise introduced by a human operator.

[0089] Preferably, the control signal is fed to a motor, in particular a motor controller of the motor, of the dosing device, wherein a movement of a discharge member of the dosing device can preferably be carried out by means of the motor. Thus, a dosing process can advantageously be influenced, for example, started or stopped, using the control signal.

[0090] Alternatively or additionally, it can also be provided that a reference object is recognizable in the first image and / or the second image, wherein the reference object has defined dimensions and / or patterns and / or is used to determine a distance, in particular a particle size of the bulk material, in the first and / or second image.

[0091] The reference object can be used to determine dimensions of structures contained in the first and / or second image if the dimensions of the reference object are known.

[0092] The reference object can represent a base or parts of it on which bulk material can be piled. For example, the reference object has a pattern, such as a checkerboard pattern. This is advantageous because a length reference is obtained using the reference object even if parts of the reference object (e.g., by bulk material) are obscured.

[0093] The reference object can, for example, have a rectangular main side and preferably be a flat and / or plate-shaped element. Such a reference object can be placed or positioned appropriately next to the bulk material sample during the image acquisition process. The reference object can have a black or white side. This is advantageous because it also provides a color reference.

[0094] The reference object can also advantageously provide information for an ML model, discussed in detail below, which ML model is used to evaluate the first and / or second image. In this case, the ML model can, for example, learn a relationship between the reference object and a particle size of the bulk material. Therefore, the reference object can also be included in the images used to train the ML model.

[0095] Alternatively or additionally, it can also be provided that the determined configuration comprises information on a model type from a selection of several model types of dosing devices, on a discharge element from a selection of several discharge elements for dosing devices and / or on settings of at least one operating parameter for dosing devices from a selection of several operating parameters.

[0096] The dosing device advantageously comprises a discharge element. The discharge element can be, for example, a screw, a conveyor belt, a plate conveyor, a spiral, a screw, and / or a slide. The selection of discharge elements for dosing devices therefore preferably includes the following discharge elements: screw, belt, plate, spiral, screw, and / or slide. The selection of operating parameters for dosing devices can include, for example, the speed of the discharge element and / or the operating temperature.

[0097] Alternatively or additionally, it can also be provided that the first recording is an image in the visible, infrared, or ultraviolet spectral range, retrieved from a memory, received by a sensor, in particular an optical one, and / or received via a data connection. The first recording can be taken with a camera. This can, for example, have a sensor that is sensitive in the visible, infrared, and / or ultraviolet spectral range. By selecting the sensor type, i.e., which spectral components of the light are recorded for the recording, different features can be determined directly based on the data of the first recording.

[0098] For example, an infrared camera can be used to determine the temperature of the bulk material, and the configuration of the dosing device for dosing this bulk material can be determined based on the temperature. For example, if the method is applied during ongoing operation of the dosing device, a temperature rise of the dosed bulk material that exceeds a threshold value can be detected. An elevated temperature can indicate an incorrect selection of the discharge element in the dosing device and thus an unsuitable configuration. The dosing process of the bulk material can then be aborted, for example, based on this detection.

[0099] Furthermore, the first image can also be taken using a radar sensor and / or an X-ray device.

[0100] The first receptacle of the bulk material to be dosed can be created, for example, before the dosing device is filled with the bulk material to be dosed. For example, the bulk material captured by the first receptacle can be located in a sealed material package. For example, the bulk material captured by the first receptacle can be located in the inlet of the dosing device and / or in a storage container from which the bulk material is taken and fed to the dosing device. In one embodiment, the bulk material captured by the first receptacle is located outside the dosing device, inside the dosing device, and / or in front of and / or behind the discharge device.

[0101] Alternatively or additionally, it can also be provided that the second recording is an image recording, preferably in the visible, infrared or ultraviolet spectral range, retrieved from a memory, received by a sensor, in particular an optical sensor, and / or received via a data connection.

[0102] The second image can advantageously be captured with a camera. This camera can, for example, have a sensor sensitive to the visible, infrared, and / or ultraviolet spectral range. By selecting the sensor type—that is, which spectral components of the light are captured for the image—different features can advantageously be determined directly based on the data from the second image.

[0103] For example, an infrared camera can be used to determine the temperature of the bulk material, and the configuration of the dosing device for dosing this bulk material can be determined based at least in part on the temperature. For example, a temperature rise of the dosed bulk material exceeding a threshold value can be detected when applying the method during ongoing operation of the dosing device. An elevated temperature can indicate an incorrect selection of the discharge element in the dosing device and thus an unsuitable configuration. The dosing process of the bulk material can then be aborted, for example, based on this detection.

[0104] Furthermore, the second image can also be taken using a radar sensor and / or an X-ray device.

[0105] The second receptacle for the bulk material to be dosed can be created, for example, before the dosing device is filled with the bulk material to be dosed. For example, the bulk material captured by the second receptacle can be located in a preferably sealed material packaging. For example, the bulk material captured by the second receptacle can be located in the inlet of the dosing device and / or in a storage container from which the bulk material is advantageously removed and fed to the dosing device. In one embodiment, the bulk material captured by the second receptacle is located outside the dosing device, inside the dosing device, and / or in front of and / or behind the discharge device.

[0106] Alternatively or additionally, the suggestion module may also include an ML model that has been pre-trained and / or is included in the configuration determination.

[0107] Advantageously, the machine learning model (ML model) is trained with data from a large number of recordings of one or more known bulk materials. In this way, a relationship can be learned between, on the one hand, a recording (of a bulk material) and, on the other hand, a specific bulk material or information about it (such as an identifier and / or a property of the bulk material) and / or a configuration of a dosing device. Optionally, in addition to the recording data, further information, for example about dosing devices (in particular about their configuration), can be provided as input data, and the training can take this information into account accordingly. This allows the learned relationship to be expanded.

[0108] The ML model preferably has, as input data and output data, at least partially the input data and output data of the suggestion module, respectively. The ML model therefore advantageously calculates the output data based on the input data. Accordingly, the ML model is advantageously trained on input data that corresponds to the input data used later.

[0109] The ML model can also have learned a relationship between identifiers (of bulk materials) on the one hand and configurations on the other. Optionally, additional information, such as dosing devices (especially their configuration), can be provided as input data, and the training can incorporate this information accordingly. This allows the learned relationship to be expanded.

[0110] To extract information from images, convolutional neural networks (CNN), especially from the field of deep learning, have proven to be advantageous and are therefore preferred as the basis for the first ML model.

[0111] The initial ML model can also be retrained using newly acquired images. This allows the reliability and quality of the resulting configuration to be continuously improved.

[0112] Alternatively or additionally, it can also be provided that the first evaluation module has an ML model that has been pre-trained and / or is included in the determination of the first and / or second bulk material property and / or the identifier.

[0113] Alternatively or additionally, it can also be provided that the second evaluation module has an ML model that has been pre-trained and / or is included in the determination of the second bulk material property.

[0114] Advantageously, the machine learning model (ML model) of the first and / or second evaluation module is trained with data from a large number of images of one or more known bulk materials. This allows a relationship to be learned between, on the one hand, an image (of a bulk material) and, on the other hand, a specific bulk material or information about it (such as an identifier or a property of the bulk material). Optionally, the relationship can also be learned with different sample configurations.

[0115] Advantageously, an ML model can be used for each of the suggestion module and the first and second evaluation modules, with the ML models being independent. In this case, it is advantageous if the ML model of the suggestion module is trained with data that results from the output of the ML model of the first and / or second evaluation module and / or that is determined based on the result data of the ML model of the first and / or second evaluation module. In this way, the ML model of the suggestion module can learn a relationship between, on the one hand, the respective output data of the first and / or second evaluation module (as well as any additional information) and, on the other hand, a configuration.

[0116] If the ML models pass, a configuration can therefore advantageously be determined using the ML model of the proposal module based on the result data of the ML model of the first and / or second evaluation module and / or the information determined based on the result data of the ML model of the first and / or second evaluation module.

[0117] To extract information from images, convolutional neural networks (CNN), especially from the field of deep learning, have proven to be advantageous and are therefore preferably used as the basis for the ML model of the first and / or second evaluation module.

[0118] The ML model of the first and / or second evaluation module can also be retrained with newly acquired images. This allows the reliability and quality of the determined configuration to be continuously improved.

[0119] The ML model of the respective evaluation module preferably has, at least in part, the input data and output data of the respective evaluation module as input data and output data, respectively. The respective ML model therefore advantageously calculates the output data based on the input data. Accordingly, the ML model is advantageously trained on input data that corresponds to the input data later used.

[0120] Alternatively or additionally, it can also be provided that the first bulk material property is at least one of the following properties of the bulk material or a measure thereof: a grain shape, a grain size, a particle size, an angle of repose, an outlet angle, a physical property, a chemical property, a moisture content, a material type, a density, a flow behavior, a tendency to bridge formation, a tendency to shoot when fluidized, a lump content, an electrostatic chargeability, a chemical instability, a temperature sensitivity, suspended in air, a tendency to demix, consisting of components, a free flowability, a tendency to agglomeration, an abrasiveness, a corrosiveness, a mechanical sensitivity, a fragility, an explosiveness, a flammability, a dustiness, a moisture, an adhesion, a consistency, a hygroscopic behavior, a temperature, a tendency to fluidize,a tendency to harden, radioactivity, toxicity, thixotropic behavior, a tendency to deteriorate, a tendency to soften, static electricity, the presence of oils and fats, flakiness and / or stickiness.

[0121] Alternatively or additionally, it can also be provided that the second bulk material property is or characterizes a haptic material property of the bulk material or is at least one of the following properties of the bulk material or a measure thereof: a grain shape, a grain size, a particle size, an angle of repose, an outlet angle, a physical property, a chemical property, a moisture content, a material type, a density, a flow behavior, a tendency to bridge formation, a tendency to shoot when fluidized, a lump content, an electrostatic chargeability, a chemical instability, a temperature sensitivity, suspended in air, a tendency to demix, consisting of components, a free flowability, a tendency to agglomeration, an abrasiveness, a corrosiveness, a mechanical sensitivity, a fragility, an explosiveness, a flammability, a dustiness, a moisture content, an adhesion, a consistency,a hygroscopic behavior, a temperature, a tendency to fluidize, a tendency to harden, a radioactivity, a toxicity, a thixotropic behavior, a tendency to spoil, a tendency to soften, static electricity, the presence of oils and fats, flakiness and / or stickiness.

[0122] Further information on bulk solids properties (in particular on material properties of bulk solids) can be found, for example, in the document "General bulk solids properties and their brief presentation" of the "FEDERATION EUROPEENNE DE LA MANUTENTION SECTION II", FEM 2 582, Original D, Edition D, November 1991, the document "Specific bulk solids properties for mechanical conveying" of the "FEDERATION EUROPEENNE DE LA MANUTENTION SECTION II", FEM 2 181, Original E, Edition D, 1989, and the document "Bulk solids properties" of the "FEDERATION EUROPEENNE DE LA MANUTENTION SECTION II", FEM 2 581, Original D, Edition D, November 1991.

[0123] Alternatively or additionally, it can also be provided that the dosing parameter is a delivery rate, in particular a target, minimum, maximum and / or average delivery rate, of the dosing device and / or is obtained via a user interface.

[0124] The feed rate of a dosing device with respect to a bulk material is preferably the quantity (in kilograms or in liters) of the bulk material that can be dosed per unit of time with the dosing device.

[0125] The object is achieved by the invention according to a second aspect in that a method for obtaining a recommendation for a configuration of a dosing device for a bulk material to be dosed, comprising that a first image of a sample of the bulk material is taken, in particular in a first sample configuration and / or with a camera, and / or a second image of the sample of the bulk material is taken, in particular in a second sample configuration and / or with a camera, and is provided in a method according to the first aspect of the invention and is obtained there as a first image and / or second image.

[0126] This makes it particularly advantageous to obtain a suitable configuration of a dosing device against the background of a bulk material to be dosed.

[0127] The camera used to take the first and second shots can be the same camera or two different cameras.

[0128] In particular, the method by which the recordings are provided can also be executed at a remote location, such as on a cloud computer. Thus, only a camera and a corresponding data connection need to be provided on the client side in order to be able to use a method according to the second aspect of the invention.

[0129] For example, the process is carried out using a smartphone. This allows operators to determine the configuration of bulk material dosing devices on the go.

[0130] Preferably, the method is computer-implemented. All advantages described with respect to the method according to the first aspect of the invention also apply correspondingly to the method according to the second aspect of the invention. Therefore, reference can be made to the previous explanations at this point.

[0131] Alternatively or additionally, it can also be provided that the method comprises (i) that the configuration determined in the method according to the first aspect of the invention is obtained as a recommendation for a configuration and / or that the control signal generated in the method according to the first aspect of the invention is obtained, (ii) that a property, in particular a material property, for example a haptic material property, of the bulk material is determined, in particular manually, and provided in the method according to the first aspect of the invention and obtained there as a data set representing a second bulk material property and / or (iii) that at least one parameter is provided in the method according to the first aspect of the invention and obtained there as a dosing parameter.

[0132] For example, the obtained configuration can be displayed on a user interface, such as a screen, and / or stored in a database.

[0133] By providing the process with further information about the bulk material, such as material properties, and / or the dosing device, such as dosing parameters, a better recommendation for a configuration can be obtained.

[0134] The object is achieved by the invention according to a third aspect in that a device for data processing is proposed, comprising means which are designed to carry out a process according to the first aspect of the invention and / or according to the second aspect of the invention.

[0135] The data processing device can comprise the suggestion module, the first evaluation module and / or the second evaluation module and / or be operatively connected to these.

[0136] All advantages and options explained with respect to the method according to the first and / or second aspect of the invention also apply correspondingly to a data processing device according to the third aspect of the invention. Therefore, reference can be made to the previous explanations in this regard.

[0137] For example, the data processing device is a cloud computing system. The data processing device may comprise or represent a distributed system.

[0138] The object is achieved by the invention according to a fourth aspect in that a dosing device is proposed which has a device for data processing according to the third aspect of the invention and / or is operatively connected thereto.

[0139] Such a dosing device makes it particularly advantageous to continuously compare the current configuration of the dosing device with the proposed configuration during operation of the dosing device and, if necessary, to make adjustments to the current configuration of the dosing device and / or to abort an ongoing dosing process and / or not to start a new dosing process.

[0140] All advantages and options explained with regard to the method according to the first aspect of the invention and with regard to the data processing device according to the third aspect of the invention also apply accordingly to a dosing device according to the fourth aspect of the invention. Therefore, reference can be made to the previous explanations in this regard.

[0141] The object is achieved by the invention according to a fifth aspect in that a device for data processing, in particular a smartphone, with a camera and further means which are designed to provide images taken with the camera in a method according to the first aspect of the invention in such a way that these are obtained there as a first recording and / or as a second recording is proposed.

[0142] The smartphone can have a screen for displaying recommendations for dosing device configurations. The data processing device can be used to carry out a method according to the second aspect of the invention.

[0143] All advantages and options explained with regard to the method according to the second aspect of the invention also apply accordingly to the data processing device according to the fifth aspect of the invention. Therefore, reference can be made to the previous explanations in this regard.

[0144] Short description of the drawings

[0145] Further features and advantages of the invention will become apparent from the following description, in which preferred embodiments of the invention are explained with reference to schematic drawings.

[0146] Showing:

[0147] Fig. 1 is a schematic representation of a prior art device

[0148] Dosing device;

[0149] Fig. 2a a first image of a sample of a bulk material in a first

[0150] Sample configuration;

[0151] Fig. 2b a second image of the bulk material sample from Fig. 2a in a second

[0152] Sample configuration;

[0153] Fig. 3 is a flowchart of a method according to the first aspect of the invention in a first embodiment;

[0154] Fig. 4 is a flowchart of a method according to the first aspect of the invention in a second embodiment;

[0155] Fig. 5 is a flowchart of a method according to the first aspect of the invention in a third embodiment;

[0156] Fig. 6 is a flowchart of a method according to the first aspect of the invention in a fourth embodiment;

[0157] Fig. 7 is a flowchart of a method according to the second aspect of the invention;

[0158] Fig. 8 is a schematic representation of a data processing device according to the third aspect of the invention;

[0159] Fig. 9 is a schematic representation of a dosing device according to the fourth aspect of

[0160] invention; and

[0161] Fig. 10 is a schematic representation of a data processing device according to the fifth aspect of the invention. Description of the Embodiments

[0162] Fig. 1 shows a schematic representation of a previously known dosing device 1.

[0163] A bulk material 3 to be dosed is fed to the dosing device 1 from a storage container 5. From the storage container 5, the bulk material passes via a selectively openable and closable connecting section 7 into a receiving container 9 of the dosing device 1, where it is present as a bulk material quantity with a surface 11. By opening the connecting section 7, bulk material can be transferred from the storage container 5 into the receiving container 9. By means of a discharge element 13, the bulk material 3 is then discharged from the dosing device 1, i.e. from the receiving container 9, in a manner known per se and leaves the latter via a vertical discharge 15. The discharge element 13 is coupled to a motor 17 and can be rotated at an adjustable, variable speed, controlled by a motor controller of the motor 17.During material discharge, a change in the weight of a system of the dosing device 1, which is weighed by a load cell 19, is used to control the speed of the discharge element 13. The dosing device described is a so-called "loss-in-weight dosing scale." The discharge element 13 can be designed as a screw conveyor, conveyor belt, or vibrating chute.

[0164] In order to dose the bulk material 3 with the dosing device 1, the dosing device 1 must be appropriately configured. This means that the appropriate type of dosing device and the corresponding components must first be selected. For this purpose, a method according to the first aspect of the invention, with which a type of dosing device and a configuration of the dosing device 1 can be determined, can be advantageously used.

[0165] Fig. 2a shows a first image 21a of a sample 23 of a bulk material to be dosed with the dosing device 1, in which the sample 23 is in a first sample configuration. To set the first sample configuration, the bulk material sample 23 was piled onto a base 25 from a defined height (e.g., 40 cm).

[0166] Fig. 2b shows a second image 21b of the bulk material sample 23, in which the sample 23 is in a second sample configuration. The bulk material sample 23 was transferred from the first to the second sample configuration by piling the bulk material sample 23 onto the base 25 again from a defined height (e.g., 80 cm).

[0167] Both images were taken from the side with an identical perspective. The sample configurations shown are two differently formed heaps 27a, 27b of the same bulk material sample 23. Due to properties, particularly material properties, of the bulk material of sample 23, the two different discharge heights result in the two differently formed heaps 27a, 27b with different heights H1 and H2 and different widths B1 and B2, which are illustrated in the two images by labeled double-headed arrows.

[0168] A reference object 29 is also visible in both images 21a, 21b. The reference object 29 is plate-shaped and mounted on a mount 31 such that the main side of the reference object 29 is captured frontally in the images 21a, 21b. The dimensions of the reference object 29 and the checkerboard pattern on the reference object 29 are known. Thus, the reference object 29 can be used to determine a distance, for example, a dimension of a structure of the bulk material, in the respective image 21a, 21b.

[0169] Fig. 3 shows a flowchart 100 of a method according to the first aspect of the invention in a first embodiment. In 101, the first image 21a is obtained, i.e., the image 21a of the sample 23 of the bulk material to be metered with the metering device 1 in a first sample configuration. For this purpose, the data from the image 21a is received, for example, via a data line or retrieved from a memory.

[0170] In 103, based on the data from the first image 21a, the type of dosing device 1 and its configuration for the bulk material of sample 23 are determined. For this purpose, the image data are processed using a suggestion module. Strictly speaking, the suggestion module is a machine learning (ML) model that, during training, has learned dosing device types and corresponding dosing device configurations based on numerous images of different bulk materials with associated type selection and configuration of a dosing device. (The images used for training each show a sample of the bulk material in a sample configuration as described for Fig. 2a, including the correspondingly positioned reference object.) The obtained image data are therefore fed to the suggestion module and thus to the ML model, and the ML model is calculated based on these image data.This results in output data at the output of the ML model that represents the configuration of the dosing device 1.

[0171] In 105, the determined configuration is output to a user on a user interface, such as a screen, and / or stored in a database.

[0172] This is used to determine the configuration of the dosing device 1 for the bulk material based on the data from the first recording 21a.

[0173] Fig. 4 shows a flowchart 200 of a method according to the first aspect of the invention in a second embodiment.

[0174] In 201, the first image 21a is obtained, i.e., the image 21a of the sample 23 of the bulk material to be dosed with the dosing device 1 in a first sample configuration. For this purpose, the data from the image 21a is received, for example, via a data line or retrieved from a memory.

[0175] In 203, the second image 21b is obtained, i.e., the image 21b of the sample 23 of the bulk material to be dosed with the dosing device in a second sample configuration. For this purpose, the data from the image 21b is received, for example, via a data line or retrieved from a memory.

[0176] At 205, based on the data from the first and second images 21a, 21b, the type of dosing device 1 and the configuration of the dosing device 1 for the bulk material of the sample 23 are determined. For this purpose, the image data are processed using a suggestion module. The suggestion module is, strictly speaking, a machine learning (ML) model that, during training, has learned dosing device types and corresponding dosing device configurations based on numerous pairs of first and second images of different bulk materials (wherein the respective images of the respective sample of the bulk material are in the first and second sample configurations described above) with an associated selection of the type and corresponding configuration of a dosing device. (The images used for training also show the correspondingly positioned reference object 29).The obtained image data is therefore fed to the suggestion module and thus to the ML model, and the ML model is calculated based on this image data. The ML model then produces output data representing the type and corresponding configuration of the dosing device 1. In 207, the determined configuration is displayed to a user on a user interface, such as a screen, and / or stored in a database.

[0177] Based on the data from the first and second recordings 21a, 21b, the configuration of the dosing device 1 for the bulk material is determined.

[0178] Fig. 5 shows a flowchart 300 of a method according to the first aspect of the invention in a third embodiment.

[0179] In 301, the first image 21a is obtained, which is again the image 21a of the sample 23 of the bulk material to be dosed with the dosing device 1 in a first sample configuration. For this purpose, the data from the image 21a is received, for example, via a data line or retrieved from a memory.

[0180] At 303, the image data is processed by a first evaluation module. Strictly speaking, the first evaluation module is a machine learning model (ML model) that, as part of a training process, has learned bulk material properties based on numerous images of different bulk materials with assigned properties. (The images used for training each show a sample of the bulk material in a sample configuration as described in Fig. 2a, including the correspondingly positioned reference object 29.) The obtained image data are therefore fed to the first evaluation module and thus to the ML model, and the ML model is calculated based on this image data. The ML model then produces output data representing a first property of the bulk material. This is a material property of the bulk material.

[0181] At 305, a data set representing a second property of the bulk material is obtained via a user input. This is another material property of the bulk material. Optionally, a dosing parameter is also obtained, for example, also via a user input. A dosing parameter can be specified, for example, as a required minimum feed rate required in the planned application scenario.

[0182] In 307, the first property, the second property, and optionally also the dosing parameter are processed using a suggestion module to determine the type of dosing device and the configuration of the dosing device for the bulk material of the sample. Strictly speaking, the suggestion module is a machine learning (ML) model that, during training, has learned dosing device configurations based on numerous different combinations of the first property, second property, and optionally dosing parameters with an associated dosing device configuration. The data (i.e., the first property, second property, and optionally also the dosing parameter) are therefore fed to the suggestion module and thus to the ML model, and the ML model is calculated based on this data. The ML model then produces output data representing the type and configuration of the dosing device.Additional data can also be provided as input data to the ML model, although this is not necessary in this case.

[0183] In 309, the determined configuration is output to a user on a user interface, such as a screen, and / or stored in a database.

[0184] For example, the second property is a material property of the bulk material that was not determined from the recording or possibly cannot be determined at all.

[0185] Based on the data from the first recording 21a, the data volume, and, if applicable, the dosing parameter, the type and configuration of the dosing device 1 for the bulk material are determined. The data from the first recording 21a are not directly processed with the data volume and the dosing parameter. Instead, the first bulk material property determined from the data from the first recording 21a is then processed together with the second bulk material property and, if applicable, the dosing parameter by feeding this data to the ML model of the proposal module as input data.

[0186] Fig. 6 shows a flowchart 400 of a method according to the first aspect of the invention in a fourth embodiment.

[0187] 401 and 403 are very similar to 301 and 303, except that in 403 the ML model of the first evaluation module has not learned bulk material properties (like the ML model in 303) during training, but rather bulk material identifiers based on numerous images of different bulk materials with assigned identifiers. (The images used for training each show a sample of the bulk material in a sample configuration as described in Fig. 2a, including the correspondingly positioned reference object 29.) The obtained image data is therefore fed to the first evaluation module and thus to the ML model, and the ML model is calculated based on this image data. The ML model then produces output data representing an identifier of the bulk material. This is an alphanumeric character string that identifies the bulk material, for example, within an ERP database.

[0188] In 405, a first property, in particular a material property, of the bulk material is retrieved from a database using the identifier.

[0189] In 407 (similar to the optional 305), a dosing parameter is obtained, for example, via user input. A dosing parameter can be specified, for example, as a required minimum flow rate required in the planned application scenario. Alternatively, the dosing parameter could also be retrieved from the database along with the first property of the bulk material, where it could also be stored for the respective bulk material.

[0190] At 409, the first property and the dosing parameter are processed using a suggestion module to determine the configuration of the dosing device for the bulk material of the sample. Strictly speaking, the suggestion module is a machine learning (ML) model that, during training, has learned configurations of dosing devices based on numerous different combinations of the first property and dosing parameter with an associated configuration of a dosing device. The data (i.e., the first property and dosing parameter) are therefore fed to the suggestion module and thus to the ML model, and the ML model is calculated based on this data. The ML model then produces output data representing the configuration of the dosing device. Additional data can also be provided as input data to the ML model, although this is not necessary in this case.

[0191] In 411, the determined configuration is output to a user on a user interface, such as a screen, and / or stored in a database.

[0192] Thus, based on the data from the first recording 21a and the dosing parameter, the configuration of the dosing device 1 for the bulk material is determined. The data from the first recording 21a are not directly processed with the dosing parameter; instead, an identifier determined from the data from the first recording enables the first bulk material property to be obtained. This first bulk material property is then processed together with the dosing parameter by feeding this data to the ML model of the suggestion module as input data. In each of the above-explained embodiments of the method according to the first aspect of the invention, a type of dosing device and the corresponding configuration of the dosing device can be determined, for example, by specifying a discharge element and / or an operating parameter of the dosing device 1 in the form of a maximum motor speed.For example, according to the determined configuration, the discharge device can be a screw and the maximum speed can be 60 revolutions per minute.

[0193] It should be noted that the reference object 29 also allows the ML model to inherently learn and exploit a relationship between bulk material parts and the reference object, which can lead to better configuration recommendations. However, in alternative embodiments, it is possible for no reference object to be placed in the images (both those obtained in the method and those used to train the respective ML model).

[0194] Fig. 7 shows a flowchart 500 of a method according to the second aspect of the invention. This method can be used to obtain a recommendation for a type of dosing device and a corresponding configuration of the dosing device 1 for a bulk material to be dosed.

[0195] In 501, a first image of a sample of the bulk material in a first sample configuration is taken with a camera (this is, for example, the first image 21a from Fig. 2a) and / or a second image of the sample of the bulk material in a second sample configuration is taken with the camera (this is, for example, the second image 21b from Fig. 2b). The reference object 29 can also be provided accordingly in each image.

[0196] At 503, the first image or the two images (in particular their image data) are provided in a method according to the first aspect of the invention and obtained there as the first image and / or the second image. For example, this could be a method as explained with reference to Figs. 3 to 6.

[0197] In 505, a configuration is obtained as a recommendation for a type of dosing device and a corresponding configuration of the dosing device 1 for the bulk material to be dosed.

[0198] Using the configuration recommendation, the dosing device 1 can be easily configured to suit the bulk material to be dosed. The process for which the image data is provided can advantageously be executed on a cloud server.

[0199] Fig. 8 shows a schematic representation of a data processing device 33 according to the third aspect of the invention.

[0200] The data processing device 33 has means configured to carry out a method according to the first and / or second aspect of the invention.

[0201] Fig. 9 shows a schematic representation of a dosing device 35 according to the fourth aspect of the invention.

[0202] The dosing device 35 may be the dosing device of Fig. 1 with a data processing device 37 according to the third aspect of the invention, such as the device 33 as described with reference to Fig. 8.

[0203] Fig. 10 shows a schematic representation of a data processing device 39 according to the fifth aspect of the invention. The data processing device 39 is a smartphone with a camera 41. The device 39 offers the operating personnel of the dosing device 1 a flexible option for determining a suitable configuration for the dosing device 1, for example, for a bulk material 3 to be dosed before it is filled into the storage container 5.

[0204] For this purpose, the data processing device 39 has means which are designed to provide images taken with the camera 41 (for example the images 21a and / or 21b) in a method according to the first aspect of the invention in such a way that they are obtained there as a first image and / or a second image.

[0205] The features disclosed in the foregoing description, in the drawings and in the claims may be essential to the invention in its various embodiments, both individually and in any combination.

[0206] List of reference symbols

[0207] 1 dosing device

[0208] 3 Bulk goods

[0209] 5 storage containers

[0210] 7 connecting section

[0211] 9 Receptacles

[0212] 11 Surface

[0213] 13 Discharge organ

[0214] 15 Vertical drop

[0215] 17 Engine

[0216] 19 Load cell

[0217] 21a, 21b recording

[0218] 23 Bulk sample

[0219] 25 base

[0220] 27a, 27b Heap

[0221] 29 Reference object

[0222] 31 Bracket

[0223] 33 Data processing device

[0224] 35 Dosing device

[0225] 37 Data processing device

[0226] 39 Data processing device

[0227] 41 Camera

[0228] 100 Flowchart

[0229] 101 Obtaining a first image of a bulk material sample

[0230] 103 Determining a dosing device configuration

[0231] 105 Output and / or save the determined configuration

[0232] 200 Flowchart

[0233] 201 Obtaining a first image of a bulk material sample

[0234] 203 Obtaining a second image of the bulk sample

[0235] 205 Determining a dosing device configuration

[0236] 207 Output and / or save the determined configuration 300 Flowchart

[0237] 301 Obtaining a first image of a bulk material sample

[0238] 303 Processing the data of the first recording with a first evaluation module and obtaining a first property of the bulk material

[0239] 305 Obtaining a data set and optionally a dosing parameter

[0240] 307 Determining a dosing device configuration

[0241] 309 Output and / or save the determined configuration

[0242] 400 Flowchart

[0243] 401 Obtaining a first image of a bulk material sample

[0244] 403 Processing the data of the first recording with a first evaluation module and obtaining an identifier of the bulk material

[0245] 405 Retrieving a first property of the bulk material from a database

[0246] 407 Obtaining a dosing parameter

[0247] 409 Determining a dosing device configuration

[0248] 411 Output and / or save the determined configuration

[0249] 500 Flowchart

[0250] 501 Picking up a first and / or second pickup of a bulk material

[0251] 503 Providing the recordings in a method according to the first aspect of the invention

[0252] 505 Obtaining a recommendation for a dosing device configuration

[0253] Bl, B2 width

[0254] Hl, H2 height

Claims

Patent claims 1. A method for providing a dosing device for a bulk material to be dosed, comprising obtaining at least a first image of at least one sample of the bulk material, and wherein, based on the data of the first image, at least one type of dosing device and a corresponding configuration of the dosing device for the bulk material is determined.

2. The method according to claim 1, wherein the method comprises that by means of a suggestion module the one type of dosing device and the corresponding configuration of the dosing device for the bulk material is determined, that the data of the first recording are included in the determination of the type and the configuration by means of the suggestion module and / or that by means of a first evaluation module a first identifier of the bulk material is determined based on the data of the first recording, and wherein the first identifier is included in the determination of the configuration by means of the suggestion module.

3. The method according to claim 2, wherein the method comprises retrieving information on the associated bulk material from a database based on the identifier and including said information in determining the configuration by means of the suggestion module.

4. Method according to one of the preceding claims, wherein the method comprises obtaining at least one data set representing a second identifier of the bulk material, wherein (i) based on the obtained data set, the type and the corresponding configuration of a dosing device for the bulk material is determined by means of the suggestion module and / or (ii) the data set is included in the determination of the type and the corresponding configuration.

5. Method according to one of the preceding claims, wherein the method comprises obtaining a second image of the sample of the bulk material, and wherein (i) the type and corresponding configuration of a dosing device for the bulk material is determined by means of the suggestion module using the data from the second image and / or (ii) the data from the second image are included in the determination of the type and the corresponding configuration of the dosing device, wherein preferably (i) the first identifier of the bulk material is determined using the first evaluation module based on the data from the first and second images, and / or (ii) a second identifier of the bulk material is determined using a second evaluation module based on the data from the first and / or second images and is included in the determination of the configuration.

6. The method according to claim 5, wherein (i) the first image and the second image are taken from different perspectives and / or (ii) the bulk material sample is in a first sample configuration during the first image and the bulk material sample is in a second sample configuration during the second image, wherein preferably between the two images the bulk material sample is transferred from the first sample configuration to the second sample configuration; wherein preferably the first and second sample configurations are two differently formed heaps of the bulk material sample and / or at least one parameter of the ambient conditions, such as ambient temperature, air humidity and / or ambient pressure, of the bulk material sample is changed between the first and second sample configuration.

7. Method according to one of the preceding claims, wherein the method comprises obtaining a dosing parameter and determining a configuration of a dosing device for the bulk material based on the dosing parameter.

8. Method according to one of the preceding claims, wherein (i) type, configurations and status data of dosing devices and / or bulk material data for the bulk materials dosed with the dosing devices are obtained, in particular from a cloud-based computer, and are taken into account, in particular in the suggestion module, when determining the type and the configuration, wherein a provisionally determined configuration is validated on the basis of the received configurations, status data and / or bulk material data and preferably, if the provisionally determined configuration does not correspond to a defined quality standard, is adapted and / or (ii) the determined configuration is compared with a current configuration of a dosing device, in particular to be used for dosing the bulk material, and preferably depending on the result of the comparison, a control signal is generated, which preferably, in particular as a control and / or regulating signal,the dosing device and / or an entity, in particular different from the dosing device.

9. A method according to any one of the preceding claims, wherein (i) the first identifier for the bulk material is at least one of the following properties of the bulk material or a measure thereof: a grain shape, a grain size, a particle size, an angle of repose, an angle of discharge, a physical property, a chemical property, a moisture content, a material type, a density, a flow behavior, a tendency to bridge, a tendency to shoot when fluidized, a clumping content, an electrostatic chargeability, a chemical instability, a temperature sensitivity, suspended in air, a tendency to segregate, consisting of components, a free flowability, a tendency to agglomerate, an abrasiveness, a corrosiveness, a mechanical sensitivity, a fragility, an explosiveness, a flammability, a dustiness, a moisture content, an adhesion, a consistency, a hygroscopic behavior, a temperature,a tendency to fluidize, a tendency to harden, radioactivity, toxicity, thixotropic behavior, a tendency to spoil, a tendency to soften, static electricity, the presence of oils and fats, flakiness, and / or stickiness; and / or (ii) the second identifier of the bulk material is or characterizes a haptic material property of the bulk material or is at least one of the following properties of the bulk material or a measure thereof: a grain shape, a grain size, a particle size, an angle of repose, an angle of discharge, a physical property, a chemical property, a moisture content, a material type, a density, a flow behavior, a tendency to bridge, a tendency to shoot when fluidized, a clumping content, an electrostatic chargeability, a chemical instability, a temperature sensitivity, suspended in air, a tendency to segregate, consisting of components,a free flowability, a tendency to agglomeration, an abrasiveness, a corrosiveness, a mechanical sensitivity, a fragility, an explosiveness, a flammability, a dustiness, a humidity, an adhesion, a consistency, a hygroscopic behavior, a temperature, a tendency to fluidize, a tendency to harden, a radioactivity, a toxicity, a thixotropic behavior, a tendency to, Spoilage, a tendency to soften, static electricity, the presence of oils and fats, flakiness and / or stickiness.

10. A method for obtaining a recommendation for a configuration of a dosing device for a bulk material to be dosed, comprising that a first image of a sample of the bulk material, in particular in a first sample configuration and / or with a camera, is taken and / or a second image of the sample of the bulk material, in particular in a second sample configuration and / or with a camera, is taken and provided in a method according to one of claims 1 to 9 and is obtained there as a first image and / or second image.

11. The method according to claim 10, wherein the method comprises (i) that the configuration determined in the method according to one of claims 1 to 9 is obtained as a recommendation for a configuration and / or that the control signal generated in the method according to one of claims 1 to 9 is obtained, (ii) that a property, in particular a material property, for example a haptic material property, of the bulk material is determined, in particular manually, and provided in the method according to one of claims 1 to 9 and obtained there as a data set representing a second bulk material property and / or (iii) that at least one parameter is provided in the method according to one of claims 1 to 9 and obtained there as a dosing parameter.

12. A data processing device comprising means configured to carry out a method according to one of claims 1 to 9 and / or 10 to 11.

13. Device for data processing, in particular a smartphone, with a camera and further means which are designed to provide images taken with the camera in a method according to one of claims 1 to 9 in such a way that they are obtained there as a first recording and / or as a second recording.

Images