Method for providing dosing device for bulk material, method for acquiring suggestion for configuration of dosing device for bulk material, and device for data processing

Abstract

The invention relates to a method for ascertaining at least one configuration of a dosing device for bulk material to be dosed, to a method for ascertaining suggestions for a configuration of a dosing device for bulk material to be dosed, and to a device for data processing.

Description

TECHNICAL FIELD

[0001] The present invention relates to a method for providing a dosing device for a bulk material to be dosed, a method for deriving a proposal for a configuration of a dosing device for a bulk material to be dosed, and a device for data processing. BACKGROUND

[0002] A dosing device for dosing a bulk material is composed of a large number of components which have to be appropriately selected and coordinated with one another depending on the bulk material to be dosed. In order to design a dosing device, it is usually necessary to detect the bulk material to be dosed in terms of its physical properties in a laboratory and to test its interaction with different embodiments of mechanical components and different settings of operating parameters in an experimental assembly. However, a reproducible and thus reliable result of such a detection is only possible with time-consuming and expensive measures which also require the involvement of specially trained personnel. SUMMARY

[0003] It is therefore an object of the present invention to overcome the described disadvantages of the prior art and to provide, in particular, an appliance with which a configuration of a dosing device suitable for dosing a corresponding bulk material can be derived in a simple and reliable manner in the case of a bulk material to be dosed.

[0004] According to a first aspect, the object is achieved by a method according to claim 1.

[0005] The configuration can be understood here on the one hand as the selection of a dosing device suitable for the material to be dosed and on the other hand as the selection or adjustment of operating parameters and components of the dosing device. First of all, it should usually be decided which type of dosing device is suitable for the relevant bulk material, in particular in view of the conveying device used. Pneumatic dosing devices (dilute phase pneumatic conveying, dense phase pneumatic conveying, etc.) and mechanical dosing devices with different discharge mechanisms, such as belt conveyors, screw conveyors, rotary vane feed wheels, etc., are available here. According to the method of the present invention, in order to ascertain a configuration of a dosing device for a bulk material to be dosed, a first photographic image of a sample of the bulk material is created and, on the basis of data of the first photographic image, a type of dosing device and / or a corresponding configuration of the dosing device for the bulk material is ascertained.

[0006] The present invention is therefore based on the surprising discovery that, based on a photographic image of a sample of the bulk material to be dosed, information about the respective bulk material can be derived, which information at least implicitly relates to one or more properties of the bulk material that influence its dosing behavior. Based on this information, a suitable 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 a configuration of the dosing device.

[0007] Therefore, the tedious testing of the bulk material with respect to its physical properties can be omitted or at least reduced. Thus, a suitable configuration of the metering device can be determined particularly quickly depending on the bulk material to be metered.

[0008] Against this background, it was particularly surprising to discover that the configuration recommendations obtained using the proposed method can sometimes outperform expert recommendations. It is clear that the information obtained from the captured images can sometimes even better describe bulk materials than conventional characteristic values, which were previously determined using laborious sample measurements on complex test benches, such as for physical parameters of the bulk material.

[0009] This method also advantageously allows existing dosing systems to be operated alternately with different bulk materials in a simple and uncomplicated manner. This is because no material-specific background knowledge is required to determine the configuration. This can increase the utilization rate of the dosing system and thus improve its economic efficiency and operational safety.

[0010] In particular, even non-experts can use the proposed method to determine the appropriate configuration of a dosing device for the bulk material to be dosed, so that they can then, for example, select the dosing device itself, components of a dosing device, and / or replace an existing dosing device based on the corresponding recommendations. Advantageously, the method can be used to fully or partially automate the configuration of a dosing device, in particular with regard to the adjustment of operating parameters.

[0011] The proposed method can also be easily applied to existing dosing systems, which need to be adapted or verified, for example, in terms of configuration, depending on the bulk material to be dosed. Essentially, it is sufficient to simply take a sample of the bulk material and evaluate it in a suitable manner. This makes the method highly flexible and applicable to a wide range of different dosing systems.

[0012] Examples of advantageous bulk materials are rocks, building materials, in particular topsoil, sand, gravel and / or cement, raw materials, in particular ore, coal, clay and / or deicing salt, foods, in particular cereals, sugar, salt, coffee and / or flour, and / or powdered materials, in particular pigments, fillers, granules and / or pellets.

[0013] The type of bulk material may be, for example, one of the following bulk material types: dust, powder, flour, grain, granules, meal, lumps, pellets, and / or others.

[0014] The method is advantageously computer-implemented.

[0015] The method can advantageously be provided as a cloud service. Therefore, extensive data processing does not have to be carried out at the site of the dosing device to be configured.

[0016] Acquiring the captured image advantageously includes acquiring data of the captured image, in particular image data. For example, the data is pixel values ​​of the captured image. The data can be received in raw format, in a pre-processed image format, and / or by a suitable light-sensitive sensor.

[0017] When reference is made in this application to the configuration of a metering device for the bulk material to be metered, this preferably means providing a type designation and / or a unique identification of at least one, in particular mechanical component, selected for the metering device, and / or at least one adjustment of an operating parameter of the metering device.

[0018] In this application, when a configuration is determined "based on" certain data, this is advantageously understood to mean that the configuration cannot be determined without this certain data. In this context, this certain data (which may be referred to as initial data) may advantageously undergo one or more data processing steps to obtain processed data. During these data processing steps, the certain data may, for example, be evaluated, reprocessed, and / or merged with other data. Other information, particularly information from other sources such as databases, may also be obtained with the aid of the certain data and / or processed data and stored as intermediate results. During the data processing steps, in addition to or in place of the certain data and / or processed data, the other information may undergo other data processing steps, including processing with other certain data. More generally, the latter means that there may be multiple different certain data, and the configuration may be determined "based on" these data, each of which may be processed separately. In certain processing steps, two or more different such initial data (or output data), optionally in processed form, may be merged and optionally used as input data for subsequent data processing.

[0019] Alternatively or in addition, it can also be provided that the method includes ascertaining a configuration of the dosing device for the bulk material with the help of a recommendation module, the data of the first photograph being taken into account when ascertaining the configuration with the help of the recommendation module, and / or ascertaining a first characteristic of the bulk material and / or an identifier of the bulk material based on the data of the first photograph with the help of a first evaluation module, and wherein the first bulk material characteristic and / or identifier is taken into account when ascertaining the configuration with the help of the recommendation module.

[0020] The identifier can be, for example, a unique identifier for a bulk material (such as an alphanumeric string, a name, or a chemical formula). Advantageously, the identifier can be used to determine, in particular by taking into account a database, other, pre-stored information about the bulk material represented by the identifier. Information about the bulk material, such as material specifications, can then be retrieved from the database based on the identifier. This will be discussed in more detail below.

[0021] Preferably, a plurality of first bulk material properties are ascertained and optionally taken into account when ascertaining the configuration. In one embodiment, the (at least one) first bulk material property is ascertained by means of an image processing and evaluation method based on the first image.

[0022] The recommendation module can be implemented, for example, in software, hardware, or a combination of both. Alternatively or additionally, the recommendation module can include a memory, a processor, a receiving device (such as for acquiring a captured image), a transmitting device (such as for transmitting a generated signal to another entity), or any combination thereof. Alternatively or additionally, the recommendation module can provide and / or make available and / or include all of the content included therein, such as, in particular, all resources required for this purpose, for example, in the form of software and / or hardware resources.

[0023] 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 include a memory, a processor, a receiving device (e.g., for acquiring the captured image), a transmitting device (e.g., for transmitting the generated signal to another entity), or any combination thereof. Alternatively or additionally, the first evaluation module can provide and / or make available and / or include all of its contents, such as, in particular, all resources required for this purpose, for example, in the form of software and / or hardware resources.

[0024] In one advantageous embodiment, the recommendation module has a first evaluation module. The first evaluation module and the recommendation module can preferably also be the same and thus a common module.

[0025] In one embodiment, the two modules are operated spatially separately from each other. This is advantageous when the two modules have different requirements for hardware and / or software resources, and thus the module with more computationally intensive operations can be run 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.

[0026] In one embodiment, the data of the first captured image are the first bulk material properties and / or the configuration of the dosing device are output data of the recommendation module. Other input and / or output data are possible, in particular those described elsewhere in this application.

[0027] Preferably, the output data of a module are obtained by the respective module at least partially in that at least the input data of the respective module are processed, such as evaluated, analyzed and / or converted into new data.

[0028] Alternatively or additionally, it may also be provided that the method includes, based on the identifier, retrieving information about the bulk material associated with the identifier from a database, in particular information having the first bulk material property, and taking this into account when determining the configuration with the aid of the recommendation module.

[0029] The additional information allows for more reliable and secure configuration determination. This also includes information about the bulk material that cannot be directly determined from the image data but can be obtained from other sources (such as databases). For this purpose, identifiers can serve as connecting links (relationships). This allows for information to be obtained based on the image data and further using other resources (such as databases).

[0030] The retrieved information may be or include, for example, a property about the bulk material, such as a first bulk material property of the bulk material.

[0031] In this case, the information is advantageously acquired, ie retrieved, for example, from a database, based on the identifier.

[0032] Thus, in one embodiment, additional information about the bulk material can be ascertained (particularly based on an identifier from a database) and taken into account for ascertaining the configuration (particularly at least partially with the aid of a recommendation module).

[0033] Preferably, the information refers to the material properties of the bulk material. Based on the material properties, the suitability of the bulk material for use in a metering device with a specific configuration (e.g., with regard to the adjustment of mechanical components and / or operating parameters) can be advantageously assessed. Therefore, it is advantageous to determine one or more material properties based on the data of the first image and using the identifier, and to take these into account when determining the configuration.

[0034] The retrieved information can advantageously be supplied to the entity and / or for example be provided to the user on a user interface, such as a screen. Thus, in addition to the configuration, for example, the reason why the configuration as recommended is performed can also be provided.

[0035] Alternatively or additionally, in one embodiment, at least the retrieved information is input data of the recommendation module. Other input and / or output data are possible, in particular those described elsewhere in this application.

[0036] Alternatively or additionally, it can also be provided that the method includes acquiring a data set representing a second characteristic of the bulk material, wherein (i) a configuration of the dosing device for the bulk material is determined with the help of a recommendation module, also based on the acquired data set, and / or (ii) the data set is taken into consideration when determining the configuration with the help of the recommendation module.

[0037] In addition to the data from the first image, the acquired data set is used to determine the configuration. The data from the first image and the data set can be processed together to determine a common intermediate value, which is then further processed to determine the configuration, or a first intermediate value can be determined from the image data and a second intermediate value from the data set, and the first and second intermediate values ​​can be further processed to determine the configuration.

[0038] The data set can, for example, represent and / or encode one or more properties of the bulk material. Alternatively or additionally, the data set can also be a preferably binary character sequence, in which each position represents a property of the bulk material. An example of such a character sequence is the binary sequence 0101011101, where the presence ("1") or absence ("0") of the corresponding property for the bulk material is encoded in this sequence for ten bulk material properties (e.g., "viscous," "electrostatic," "granular," etc.).

[0039] Alternatively or additionally, in one embodiment, the acquired data set is input data for the recommendation module. Other input and / or output data are possible, in particular those described elsewhere in this application.

[0040] Alternatively or additionally, provision can also be made for the data set to be acquired by user input, in particular via a human-machine interface.

[0041] Alternatively or in addition, it can also be provided that the method includes acquiring a second picture of a sample of the bulk material, and wherein (i) the configuration of the dosing device for the bulk material is ascertained based on the data of the second picture with the help of a recommendation module, and / or (ii) the data of the second picture is taken into consideration when ascertaining the configuration with the help of the recommendation module, wherein preferably (i) a first characteristic of the bulk material and / or an identifier of the bulk material is ascertained based on the data of the first picture and the second picture with the help of a first evaluation module, and / or (ii) a second characteristic of the bulk material is ascertained based on the data of the first picture and / or the second picture with the help of a second evaluation module, and said second characteristic is taken into consideration when ascertaining the configuration with the help of the recommendation module.

[0042] Therefore, in addition to the data of the first picture (and the acquired data set if necessary), the data of the second picture can also be used to ascertain the configuration.

[0043] Preferably, the data from the first picture is not used to determine the second characteristic. For example, the second characteristic can then be determined based on the data from the second picture by feeding the data from the second picture instead of the data from the first picture to the data input of the corresponding evaluation module. Preferably, further input data can be provided, where these data are not the data from the first picture.

[0044] It may also be advantageous to use the data from the first and second images to determine the first and / or second bulk material properties. To this end, the data from the first and second images may be fed to a data input of the corresponding evaluation module. Preferably, further input data may be provided.

[0045] The first property and / or the second property ascertained here is advantageously a property that differs from the property explained above and represented by the acquired data set.

[0046] 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 include a memory, a processor, a receiving device (e.g., for acquiring the captured image), a transmitting device (e.g., for transmitting the generated signal to another entity), or any combination thereof. Alternatively or additionally, the second evaluation module can be provided and / or available and / or include all of its contents, such as, in particular, all resources required for this purpose, for example, in the form of software and / or hardware resources.

[0047] In an advantageous embodiment, the recommendation module has a second evaluation module. The second evaluation module and the recommendation module can preferably also be the same and thus a common module.

[0048] In one embodiment, the two modules are operated spatially separately from each other. This is advantageous when the two modules have different requirements for hardware and / or software resources, and thus the module with more computationally intensive operations can be run 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.

[0049] It is also possible that the first evaluation module, the second evaluation module and the recommendation module are identical and / or that the first evaluation module and the second evaluation module are identical.

[0050] In one embodiment, at least the data of the second picture are input data of the first evaluation module. Other input and / or output data are possible, in particular those described elsewhere in this application.

[0051] Alternatively or additionally, in one embodiment, at least the data of the first and / or second pictures are input data and / or the second characteristic is output data of the second evaluation module. Other input and / or output data are possible, in particular those described elsewhere in this application.

[0052] Alternatively or additionally, in one embodiment, the data of the second image and / or the second characteristic are input data for the recommendation module. Other input and / or output data are possible, in particular those described elsewhere in this application.

[0053] Alternatively or in addition, it can also be provided that (i) the first recording and the second recording are preferably performed simultaneously or temporally successively from different viewing angles, and / or (ii) the bulk material sample is in a first sample configuration during the first recording and 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.

[0054] For example, the first and second pictures may be taken with the same camera, and the position and / or orientation of the camera may be changed between pictures so that the two pictures are taken temporally successively from different perspectives.

[0055] For example, the first picture and the second picture can be taken with different photographing devices, wherein the photographing devices have different positions and / or orientations. Therefore, the two pictures can be taken simultaneously from different viewing angles in a particularly advantageous manner.

[0056] In one embodiment, the viewing angles of the two captured images are the same.

[0057] A sample arrangement is preferably understood to mean the manner in which the bulk material of the sample is spatially arranged, in particular under the existing boundary conditions, for example the existing environmental conditions, and / or the formation of material accumulations (for example agglomerates) within the arrangement.

[0058] For example, a bulk material sample can be accumulated on a flat substrate from a supply pipe at a specific height. The manner and method of forming the bulk material sample pile can then be understood as the sample configuration. This sample configuration can differ from another sample configuration achieved when a bulk material sample from a different height is accumulated on the flat substrate. Instead of height, the tilt angle of the substrate can also be varied.

[0059] Alternatively or in addition, it can also be provided that the first sample configuration and the second sample configuration are two differently constructed piles of the bulk material sample, and / or at least one parameter of the environmental conditions of the bulk material sample, such as the ambient temperature, air humidity and / or ambient pressure, changes between the first sample configuration and the second sample configuration.

[0060] Preferably, the bulk material is in equilibrium with the respective existing physical environmental conditions in both sample configurations.

[0061] For example, a sample can be used to form a pile at two different ambient temperatures (preferably using the same procedure). The different pile configurations in the two cases represent different sample configurations. The bulk material of the sample is at the respective ambient temperature, i.e., in equilibrium within this range.

[0062] Another possible environmental condition is the slope (also mentioned above) of the substrate on which the bulk material sample is deposited.

[0063] Alternatively or additionally, it can also be provided that the method includes evaluating and / or analyzing the data of the first and / or second images using digital image analysis methods in the field of machine learning, in particular in order to determine the first characteristic, the second characteristic, the identifier and / or the configuration.

[0064] Advantageously, the digital image analysis is performed using machine learning methods. To this end, a machine learning model can be trained on training data, which is of the type of input data to be expected later, with correspondingly associated expected output data, and the trained model can be used to calculate output data from the corresponding input data, the output data being the corresponding specific information or other information.

[0065] The recommendation module can therefore in particular carry out a corresponding method on at least the data of the first picture and / or the second picture, for example in order to ascertain the configuration.

[0066] The first evaluation module can therefore carry out a corresponding method on the data of the first and / or second pictures, for example in order to ascertain a first property of the bulk material, a second property of the bulk material and / or an identifier.

[0067] Thus, the second evaluation module can, for example, carry out a corresponding method on the data of the first and / or second images in order, for example, to ascertain a first property and / or a second property of the bulk material.

[0068] Alternatively or additionally, it may also be provided that the method includes determining dosing parameters and, based on the dosing parameters, determining a configuration of the dosing device for the bulk material with the aid of a recommendation module.

[0069] In addition to the data of the first picture (and optionally the acquired data set and / or the data of the second picture), the quantitative allocation parameters are used to determine the configuration.

[0070] For example, a maximum speed and / or minimum dimensions of the discharge mechanism of a dosing device can be predefined for a specific bulk material (in particular, the bulk material to be dosed). Thus, the configuration can be determined based on the corresponding restrictions, so that configurations with higher speeds and / or configurations with discharge mechanisms that do not meet the minimum dimensions are not determined.

[0071] The quantitative allocation parameter can for example represent a typical characteristic variable of a quantitative allocation device. Examples of this are the target value, actual value, maximum value and / or minimum value of an operating variable. Therefore, when determining a configuration, the performance of the quantitative allocation device can be advantageously considered. Therefore, for example, the configuration can be determined based on a specific bulk material (which can be represented by the identifier discussed above) and taking the quantitative allocation parameter into consideration.

[0072] Alternatively or additionally, in one embodiment, at least the dosing parameter is input data for the recommendation module. Other input and / or output data are possible, in particular those described elsewhere in this application.

[0073] Alternatively or additionally, it may also be provided that a control signal representing the determined configuration is generated and supplied as a configuration suggestion to the entity and / or output to a user on a human-machine interface, such as a screen, and / or that the dosing device is configured based on the determined configuration.

[0074] The control signal advantageously enables the supply of information to an entity about the ascertained configuration. The entity can be, for example, a high-level quantitative dispensing device monitoring system and / or a quantitative dispensing device management system. Alternatively or additionally, the control signal can be supplied to an entity to initiate monitoring of the quantitative dispensing device and / or for documentation purposes. In this way, the configuration can advantageously be continuously acquired, in particular depending on the bulk material and / or changing operating parameters, and optionally updated or compared with the current configuration, even during the ongoing operation of the quantitative dispensing device.

[0075] The entity can be the quantitative dispensing device for which the ascertained configuration is, or a component thereof, for example a motor or a motor control thereof. The entity can also be a device other than the quantitative dispensing device.

[0076] In one embodiment, the control signal can be an analog or digital signal. Alternatively or additionally, the control signal can also be an instruction within a software application.

[0077] Alternatively or additionally, it can also be provided that the configuration and status data of the quantitative dispensing device and / or bulk material data about the bulk material with which the quantitative dispensing device respectively dispenses are acquired from a cloud-based computer and taken into account in the ascertaining of the configuration in the recommendation module, wherein the temporarily ascertained configuration is verified depending on the acquired configuration, status data and / or bulk material data, and is adjusted if it does not correspond to the defined quality criterion.

[0078] In this way, information about the respective configuration of the quantitative dispensing device in production use, status data and the bulk material with which it respectively dispenses can be acquired by the quantitative dispensing device in production use and advantageously used as feedback information in the ascertaining of the configuration. In this way, information from production use can advantageously be taken into account when deciding on the configuration. Here, a data item comprising the configuration, status data and bulk material data is preferably acquired for each pairing of the quantitative dispensing device and the bulk material with which it respectively dispenses.

[0079] If, for example, in the determined configuration, the quantitative dispensing process of the determined bulk material often (for example, in the case of more than 10%, more than 30%, more than 50% or more than 70%) results in a status code indicating impaired operation of the respective quantitative dispensing device, this combination of configuration and bulk material can be avoided and no longer ascertained as a configuration in the method.

[0080] It is also particularly advantageous that the identified configuration can be checked with feedback information. Thus, first of all the configuration of the dosing device can be identified as a temporary configuration for the bulk material, which is then checked in accordance with the acquired feedback information. If it is then confirmed that the combination of the temporary configuration and the bulk material often, for example in more than 10%, more than 30%, more than 50% or more than 70%, leads to a status code which indicates that the operation of the dosing device is impaired, the temporary configuration can advantageously be adjusted and the adjusted configuration can be identified as a configuration or, alternatively, a new temporary configuration can be identified.

[0081] Alternatively or additionally it can also be provided that the identified configuration is compared with the current configuration of the dosing device for the dosing of the bulk material and that a control signal is generated as a function of the result of the comparison, which is supplied to the dosing device and / or to an entity different from the dosing device as a manipulation and / or control signal.

[0082] In this way, the operation of the dosing device can be designed to be more reliable and safer, since the identified configuration can be used to monitor the dosing device and its dosing process. Thus, in the event of a deviation of the identified configuration for the dosing device from the current configuration of the dosing device, a corresponding control signal can be generated.

[0083] Thus, the method is particularly advantageously suitable for monitoring the use of bulk material in the context of the dosing process of the dosing device. Thus, the configuration identified as a function of the bulk material to be dosed is compared with the current configuration of the dosing device and, optionally, an alarm signal can be generated if a deviation from the defined or definable quality characteristic value is confirmed. In this way, it is possible to identify bulk material to be dosed which is not suitable for dosing with the dosing device in the current configuration. The alarm signal can be used to inform the operating and / or monitoring personnel and, optionally, to prompt them to take action and / or to abort the ongoing dosing process.

[0084] It is also advantageous thereby that the bulk material supplied to the dosing device can be continuously monitored and that, if the properties of the bulk material have changed and thus the existing configuration of the dosing device no longer meets the defined quality criteria, a new configuration is proposed for the dosing device in question and / or the ongoing dosing process is aborted. Thereby, the safety and reliability of the dosing process can be further improved with the method.

[0085] Above all, in order to achieve this safety, essentially no structural changes to the respective dosing device are required. It is sufficient, after all, to acquire a photographic picture of the bulk material. Thereby, the method can be used for a plurality of already existing dosing devices and is very flexible.

[0086] Thus, by monitoring the bulk material to be dosed, incorrect filling of the dosing device can be avoided or detected early. This makes it possible to avoid critical situations, including production downtime, more reliably than before. Unmanned and / or remotely controlled dosing processes can also be monitored better and more reliably, thereby avoiding or at least limiting costly production defects.

[0087] This method also advantageously allows existing dosing equipment to be operated alternately with different bulk materials in a simple and uncomplicated manner. For example, in one embodiment, the dosing equipment can be automatically reconfigured based on the determined configuration. This can increase the utilization rate of the dosing equipment and thus improve its economic efficiency and operational safety.

[0088] Rather, the method allows the corresponding monitoring of the metering device to be fully or partially automated, and thus further reduces or completely eliminates the susceptibility to errors introduced by human operators.

[0089] Preferably, the control signal is supplied to the motor of the quantitative dispensing device, in particular the motor control part of the motor, wherein the movement of the discharge mechanism of the quantitative dispensing device can preferably be performed by means of the motor.Thus, the quantitative dispensing process can advantageously be influenced, such as started or ended, by means of the control signal.

[0090] Alternatively or additionally, provision can also be made for a reference object to be identified in the first and / or second recording, wherein the reference object has defined dimensions and / or pattern and / or is used to determine a stretch, in particular a particle size, of the bulk material in the first and / or second recording.

[0091] If the dimensions of the reference object are known, the reference object can be used to determine the dimensions of the structure contained in the first and / or second picture, respectively.

[0092] The reference object can be a substrate or a portion thereof, onto which the bulk material can be deposited. For example, the reference object can have a pattern, such as a checkerboard pattern. This is advantageous because a length reference can be obtained using the reference object even if areas of the reference object are obscured, such as by the bulk material.

[0093] The reference object can, for example, have rectangular main sides and can preferably be a planar and / or plate-shaped element. Such a reference object can be placed near the bulk material sample or appropriately positioned when the image is taken. The reference object can have black or white sides. This is advantageous because a color reference is then also obtained.

[0094] The reference object can also advantageously provide information for the ML model discussed in detail below, namely, which ML model is used to evaluate the first and / or second images, respectively. In this case, the ML model can, for example, learn the correlation between the reference object and the 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 ascertained configuration includes information about a model type selected from a plurality of model types of a metering device, information about a discharge mechanism selected from a plurality of discharge mechanisms for a metering device and / or information about a setting of at least one operating parameter selected from a plurality of operating parameters for a metering device.

[0096] The quantitative distribution device advantageously has a discharge mechanism. The discharge mechanism can be, for example, a screw, a conveyor belt, a plate conveyor belt, a spiral, a screw connection and / or a slide. Therefore, the selection of discharge mechanisms for the quantitative distribution device preferably includes the following discharge mechanisms: a screw, a belt, a plate, a spiral, a screw connection and / or a slide. The selection of operating parameters for the quantitative distribution device can include, for example, the speed and / or operating temperature of the discharge mechanism.

[0097] Alternatively or additionally, it can also be provided that the first recorded image is a recorded image in the visible, infrared or ultraviolet spectral range, retrieved from a memory, received by, in particular, an optical sensor and / or received via a data connection.

[0098] The first image can be taken with a camera. This can, for example, have a sensor sensitive in the visible, infrared, and / or ultraviolet spectral range. By selecting the sensor type, i.e., which spectral portions of the light used to take the image are captured, various features can be determined directly based on the data from the first image.

[0099] For example, an infrared camera can be used to determine the temperature of the bulk material, and based on this temperature, the configuration of the dosing device used to dispense the bulk material can be ascertained. For example, when applying this method, during the ongoing operation of the dosing device, it is possible to detect heating of the dispensed bulk material, such as exceeding a threshold value. An elevated temperature can indicate that the incorrect discharge mechanism has been selected in the dosing device, and therefore that the configuration is inappropriate. Based on this determination, the bulk material dosing process can then be aborted, for example.

[0100] Furthermore, the first recorded image can also be recorded with the aid of a radar sensor and / or an X-ray device.

[0101] For example, a first image of the bulk material to be dosed can be taken before the dosing device is loaded with the bulk material. For example, the bulk material captured by the first image can be located in a sealed material package. For example, the bulk material captured by the first image can be located at the inlet of the dosing device and / or in a storage container from which the bulk material is removed and supplied to the dosing device. In one embodiment, the bulk material captured by the first image is located outside the dosing device, inside the dosing device, and / or in front of and / or behind a discharge mechanism.

[0102] Alternatively or additionally, it can also be provided that the second picture is a picture, preferably in the visible, infrared or ultraviolet spectral range, retrieved from a memory, received by, in particular, an optical sensor and / or received via a data connection.

[0103] The second image can advantageously be captured using a camera. This can, for example, include a sensor sensitive in the visible, infrared, and / or ultraviolet spectral range. By selecting the sensor type, i.e., the spectral portion of the light used to capture the image, various features can advantageously be determined directly based on the data from the second image.

[0104] For example, the temperature of the bulk material can be ascertained using an infrared camera, and the configuration of the dosing device used to dispense the bulk material can be ascertained, at least in part, based on the temperature. For example, when applying this method, during the ongoing operation of the dosing device, it can be determined that the bulk material being dispensed has heated up, for example by exceeding a threshold value. This elevated temperature can indicate that the incorrect discharge mechanism has been selected in the dosing device, and therefore that the configuration is unsuitable. Based on this determination, the bulk material dosing process can then be aborted, for example.

[0105] Furthermore, the second image can also be recorded with the aid of a radar sensor and / or an X-ray device.

[0106] For example, a second image of the bulk material to be dosed can be taken before the dosing device is loaded with the bulk material to be dosed. For example, the bulk material captured by the second image can be located in a preferably closed material package. For example, the bulk material captured by the second image can be located at the inlet of the dosing device and / or in a storage container, from which the bulk material is advantageously removed and supplied to the dosing device. In one embodiment, the bulk material captured by the second image is located outside the dosing device, inside the dosing device, and / or in front of and / or behind the discharge mechanism.

[0107] Alternatively or additionally, it can also be provided that the recommendation module has an ML model that has been pretrained and / or is taken into consideration when determining the configuration.

[0108] Advantageously, a machine learning model (ML model) is trained using data from multiple images of one or more known bulk materials. This allows for learning the associations between images (of the bulk material) on the one hand, and specific bulk materials or information about them (such as their properties and / or identifiers) and / or the configuration of the metering device on the other hand. Optionally, in addition to the image data, other information, such as information about the metering device (particularly information about its configuration), can be provided as input data, and the training can accordingly take this information into account. This allows for expanding or modifying the learned associations.

[0109] The ML model preferably uses, at least in part, the input data and output data of the recommendation module as input data and output data, respectively. Thus, the ML model advantageously calculates output data based on the input data. Accordingly, the ML model is advantageously trained on input data corresponding to the input data to be used later.

[0110] The ML model can also learn the association between the (bulk material) identifier on the one hand and the configuration on the other. Optionally, other information, such as information about the dosing device (particularly information about its configuration), can be provided as input data and appropriately considered during training. This allows for expanded learned associations.

[0111] Convolutional neural networks (CNNs), in particular from the field of deep learning, have proven to be advantageous for acquiring information from images and are therefore preferably used as the basis for the first ML model.

[0112] The first ML model can also be retrained with pictures taken later, thereby continuously improving the reliability and quality of the determined configuration.

[0113] Alternatively or additionally, it can also be provided that the first evaluation module has an ML model which has been pretrained and / or is taken into consideration when determining the first and / or second bulk material property and / or identifier.

[0114] Alternatively or additionally, it can also be provided that the second evaluation module has an ML model which has been pretrained and / or is taken into consideration when determining the second bulk material property.

[0115] Advantageously, the machine learning model (ML model) of the respective first and / or second evaluation module is trained using data from a plurality of images of one or more known bulk materials. This allows for learning associations between images (of the bulk material) on the one hand and specific bulk materials or information about them (such as properties or identifiers of the bulk material) on the other hand. Alternatively, associations with different sample configurations can also be learned.

[0116] Advantageously, the ML model can be used in the recommendation module and the first and second evaluation modules, respectively, wherein the ML models are independent. In this case, the ML model of the recommendation module is advantageously trained using data derived from the output of the ML model of the first and / or second evaluation module and / or data ascertained 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 recommendation module can learn the correlation between the corresponding output data of the first and / or second evaluation module (and optionally other additional information) on the one hand and the configuration on the other.

[0117] Therefore, when an ML model exists, the configuration can be advantageously determined using the ML model of the recommendation module based on the result data of the ML model of the first and / or second evaluation module and / or information determined based on the result data of the ML model of the first and / or second evaluation module.

[0118] Convolutional neural networks (CNNs), in particular from the field of deep learning, have proven to be advantageous for acquiring information from images and are therefore preferably used as the basis for the ML models for the first and / or second evaluation module, respectively.

[0119] The ML models of the first and / or second evaluation module can also be retrained with pictures taken again later, thereby enabling the reliability and quality of the determined configuration to be continuously improved.

[0120] The ML model of the respective evaluation module preferably uses, at least in part, the input data and output data of the respective evaluation module as input data and output data, respectively. Thus, the respective ML model advantageously calculates output data based on the input data. Accordingly, the ML model is advantageously trained on input data corresponding to the input data to be used later.

[0121] 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: particle shape, particle size, particle size, angle of repose, discharge angle, physical properties, chemical properties, moisture content, material type, density, flow behavior, arching tendency, gushing tendency in the fluidized state, lump content, electrostatic accumulation, chemical instability, temperature sensitivity, floatability in air, separation tendency, composition of components, free flowability, agglomeration tendency, abrasiveness, corrosiveness, mechanical sensitivity, brittleness, explosiveness, flammability, dustiness, humidity, adhesion, viscosity, hygroscopic behavior, temperature, fluidization tendency, hardening tendency, radioactivity, toxicity, thixotropic behavior, putrefaction tendency, softening tendency, static electricity, presence of grease, flaking and / or stickiness.

[0122] Alternatively or additionally, it can also be provided that the second bulk material property is a tactile material property of the bulk material or is characterized as or is at least one of the following properties of the bulk material or a measure thereof: particle shape, particle size, particle size, angle of repose, discharge angle, physical properties, chemical properties, moisture content, material type, density, flow behavior, arching tendency, gushing tendency in the fluidized state, lump content, electrostatic accumulation, chemical instability, temperature sensitivity, floatation in air, separation tendency, composition of components, free flowability, agglomeration tendency, abrasiveness, corrosiveness, mechanical sensitivity, brittleness, explosiveness, flammability, dustiness, humidity, adhesion, viscosity, hygroscopic behavior, temperature, fluidization tendency, hardening tendency, radioactivity, toxicity, thixotropic behavior, putrefaction tendency, softening tendency, static electricity, presence of grease, flaking and / or stickiness.

[0123] Further information on the properties of bulk materials, in particular on the material properties of bulk materials, can be found, for example, in the document “General properties of bulk materials and an overview thereof” in “FEDERATION EUROPEENNE DE LA MANUTENTION SECTION II”, FEM 2 582, Original D, Ausgabe D, November 1991, in the document “Specific properties of bulk materials in mechanical conveying” in “FEDERATION EUROPEENNE DE LA MANUTENTION SECTION II”, FEM 2 181, Original E, Ausgabe D, 1989, and in the document “Properties of bulk materials” in “FEDERATION EUROPEENNE DE LA MANUTENTION SECTION II”, FEM 2 581, Original D, Ausgabe D, November 1991.

[0124] Alternatively or additionally, it can also be provided that the dosing parameter is a delivery intensity of the dosing device, in particular a target delivery intensity, a minimum delivery intensity, a maximum delivery intensity and / or an average delivery intensity, and / or is acquired via a user interface.

[0125] The conveying intensity of the metering device relative to the bulk material is preferably the amount of bulk material (in kilograms or liters) that can be metered per unit time by the metering device.

[0126] This object is achieved according to the second aspect of the present invention in that a method for obtaining a proposal for the configuration of a dosing device for bulk material to be dosed is proposed, the method comprising taking a first picture of the bulk material, in particular a sample in a first sample configuration and / or taking a picture with a camera, and / or taking a second picture of the bulk material, in particular a sample in a second sample configuration and / or taking a picture with a camera, which is provided in the method according to the first aspect of the invention and is obtained there as a first picture and / or a second picture.

[0127] This is particularly advantageous in that a suitable configuration of the metering device can be obtained for the bulk material to be metered.

[0128] The camera used to take the first photograph and the second photograph may be the same camera or two different cameras.

[0129] In particular, the method in which the picture recording is provided can also be implemented at a remote location, such as on a cloud computing server. In order to be able to use the method according to the second aspect of the invention, only one camera and a corresponding data connection must be provided on the client side.

[0130] For example, the method can be implemented using a smartphone. This allows the operator to determine the configuration of the metering device for bulk goods in a mobile manner.

[0131] Preferably, the method is computer-implemented.

[0132] 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.

[0133] Alternatively or in addition, it can also be provided that the method includes (i) obtaining a configuration ascertained in the method according to the first aspect of the invention as a suggestion for a configuration and / or obtaining a control signal generated in the method according to the first aspect of the invention, (ii) in particular manually ascertaining properties of the bulk material, in particular material properties, such as tactile material properties, and providing them in the method according to the first aspect of the invention and obtaining them there as a data set representing properties of the second bulk material, and / or (iii) at least one parameter is provided in the method according to the first aspect of the invention and obtained there as a dosing parameter.

[0134] For example, the acquired configuration may be displayed on a user interface such as a screen, and / or stored in a database.

[0135] By providing the method with additional information about the bulk material, such as material properties, and / or about the dosing device, such as dosing parameters, better suggestions for the configuration can be obtained.

[0136] According to a third aspect of the present invention, this object is achieved in that a device for data processing is specified, which has means for carrying out the method according to the first aspect of the invention and / or the second aspect of the invention.

[0137] The device for data processing can have a recommendation module, a first evaluation module and / or a second evaluation module and / or be operatively connected to these modules.

[0138] All advantages and options explained with respect to the method according to the first and / or second aspects of the invention also apply correspondingly to the device for data processing according to the third aspect of the invention.

[0139] For example, the device for data processing is a cloud computer system. The device for data processing may have or be a distributed system.

[0140] This object is achieved according to a fourth aspect of the invention in that a metering device is provided which comprises a device for data processing according to the third aspect of the invention and / or is operatively connected to the data processing device.

[0141] Such a metering device can particularly advantageously achieve that during operation of the metering device, the current configuration of the metering device is continuously compared with the recommended configuration and, if necessary, the current configuration of the metering device is adjusted and / or an ongoing metering process is terminated and / or a new metering process is not started.

[0142] All advantages and options explained with respect to the method according to the first aspect of the invention and with respect to the device for data processing according to the third aspect of the invention also apply correspondingly to the metered-dispensing device according to the fourth aspect of the invention.

[0143] This object is achieved according to the fifth aspect of the present invention in that a device for data processing, in particular a smartphone, is proposed, which has a camera and other devices, which are configured to provide images taken with the camera in the method according to the first aspect of the invention, so that these images are acquired there as first pictures and / or as second pictures.

[0144] The smartphone may have a screen for outputting suggestions for configuring the dosing device.The method according to the second aspect of the invention may be implemented using the device for data processing.

[0145] All advantages and options explained with respect to the method according to the second aspect of the invention also apply correspondingly to the device for data processing according to the fifth aspect of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0146] Further features and advantages of the invention are apparent from the following description, in which preferred embodiments of the invention are explained with reference to the accompanying schematic drawings.

[0147] Here it is shown:

[0148] Figure 1 A schematic diagram of a dosing device known from the prior art is shown;

[0149] Figure 2a showing a first photograph of a sample of bulk material in a first sample configuration;

[0150] Figure 2b Shown from Figure 2a a second photograph of the bulk material sample in a second sample configuration;

[0151] Figure 3 A flow chart showing a method according to a first aspect of the present invention in a first embodiment is shown;

[0152] Figure 4 A flow chart showing a method according to a second embodiment of the present invention;

[0153] Figure 5 A flowchart showing a method according to the first aspect of the present invention in a third embodiment is shown;

[0154] Figure 6A flowchart showing a fourth embodiment of the method according to the first aspect of the present invention is shown;

[0155] Figure 7 A flow chart showing a method according to the second aspect of the present invention;

[0156] Figure 8 A schematic diagram showing an apparatus for data processing according to a third aspect of the present invention;

[0157] Figure 9 A schematic diagram showing a dosing device according to a fourth aspect of the present invention; and

[0158] Figure 10 A schematic diagram of an apparatus for data processing according to a fifth aspect of the present invention is shown. DETAILED DESCRIPTION

[0159] Figure 1 A schematic diagram of a previously known dosing device 1 is shown.

[0160] The bulk material 3 to be metered is supplied from a storage container 5 to a metering device 1. From the storage container 5, the bulk material enters a receiving container 9 of the metering device 1 via a selectively openable and closable connecting section 7, where the bulk material is present in a bulk material quantity having a surface 11. By opening the connecting section 7, the bulk material can be transferred from the storage container 5 to the receiving container 9. The bulk material 3 is then discharged from the metering device 1, i.e., from the receiving container 9, via a discharge mechanism 13 in a manner known per se, and exits there via a vertical tipping section 15. The discharge mechanism 13 is coupled to a motor 17 and can be rotated at an adjustable, variable speed, controlled by the motor control unit of the motor 17. During material discharge, changes in the weight of the metering device 1, which is weighed by a weighing unit 19, are used to control the speed of the discharge mechanism 13. The described metering device is a so-called "differential metering scale." The discharge mechanism 13 can be configured as a screw, a conveyor belt, or a vibrating trough.

[0161] In order to dose bulk material 3 using dosing device 1, dosing device 1 must be appropriately configured. This means that the appropriate type of dosing device and the appropriate components must first be selected. To this end, the method according to the first aspect of the present invention can be advantageously used, which allows the type of dosing device and the configuration of dosing device 1 to be determined.

[0162] Figure 2aA first photograph 21a of a sample 23 of bulk material to be dosed using the dosing device 1 is shown, in which the sample 23 is in a first sample configuration. To establish the first sample configuration, a bulk material sample 23 from a defined height (eg 40 cm) is deposited onto a base 25 .

[0163] Figure 2b A second image 21b of the bulk material sample 23 is shown, in which the sample 23 is in a second sample configuration. The bulk material sample 23 is transferred from the first sample configuration to the second sample configuration by depositing the bulk material sample 23 again from another defined height (eg 80 cm) onto the substrate 25 .

[0164] Both images were taken from the side at the same viewing angle. The sample configuration shown here is two differently constructed piles 27a, 27b of the same bulk material sample 23. Due to the properties of the bulk material of sample 23, in particular the material properties, two differently constructed piles 27a, 27b with different heights H1 and H2 and different widths B1 and B2 result for two different dumping heights. These different heights and widths are indicated in the two images by the marked double-headed arrows.

[0165] Reference object 29 can also be seen in both images 21a and 21b. Reference object 29 is plate-shaped and fastened to a holder 31 so that its main side is captured in images 21a and 21b from the front. The dimensions of reference object 29 and the checkerboard pattern on reference object 29 are known. Reference object 29 can thus be used in the corresponding images 21a and 21b to determine the dimensions of a structure, such as a bulk material.

[0166] Figure 3 A flow chart 100 shows a method according to a first aspect of the present invention in a first embodiment.

[0167] In 101, a first picture 21a is acquired, namely a picture 21a of a sample 23 of bulk material to be dosed using the dosing device 1 in a first sample configuration. To this end, the data of the picture 21a are received, for example, via a data line or retrieved from a memory.

[0168] At 103, the type of dosing device 1 and its configuration for the bulk material of the sample 23 are ascertained based on these data of the first image 21a. To this end, the image data is processed by a recommendation module. The recommendation module is more specifically a machine learning model (ML model) that has learned the type of dosing device and the corresponding configuration of the dosing device during training based on a large number of images of different bulk materials, along with the associated configuration and specific selection of the dosing device. (The images used for training here each show the bulk material in a position such as the one described above.) Figure 2a The image data thus acquired are supplied to the recommendation module and thus to the ML model, and the ML model is calculated on the image data. Output data is then obtained at the output of the ML model, which represents the configuration of the dosing device 1.

[0169] At 105 , the ascertained configuration is output to the user on a user interface such as a screen and / or stored in a database.

[0170] The configuration of the metering device 1 for the bulk material is thus ascertained based on the data of the first image 21 a .

[0171] Figure 4 A flow chart 200 shows a method according to a second embodiment of the first aspect of the present invention.

[0172] In 201, a first picture 21a is acquired, namely a picture 21a of a sample 23 of bulk material to be dosed using the dosing device 1 in a first sample configuration. To this end, the data of the picture 21a are received, for example, via a data line or retrieved from a memory.

[0173] In 203, a second image 21b is acquired, which is a image 21b of a sample 23 of bulk material to be dosed by the dosing device in a second sample configuration. To this end, the data of the image 21b is received, for example, via a data line or retrieved from a memory.

[0174] At 205 , the type of dosing device 1 and its configuration for the bulk material of sample 23 are ascertained based on the data from the first and second images 21a and 21b. To this end, the image data is processed by a recommendation module. Specifically, the recommendation module is a machine learning model (ML model) that has learned the type of dosing device and its corresponding configuration during training based on numerous pairs of first and second images of different bulk materials (wherein, in corresponding images of corresponding samples of the bulk material, they are in the first and second sample configurations described above), along with the associated type selection and corresponding configuration of the dosing device. (The images used for training also show correspondingly placed reference objects 29 ). The acquired image data is thus supplied to the recommendation module and, thus, to the ML model, which is then calculated on this image data. Output data representing the corresponding configuration of dosing device 1 is then obtained at the output of the ML model.

[0175] In 207 , the ascertained configuration is output to the user on a user interface such as a screen and / or stored in a database.

[0176] The configuration of the metering device 1 for the bulk material is thus ascertained based on the data of the first image 21 a and the second image 21 b .

[0177] Figure 5 A flow chart 300 shows a third embodiment of the method according to the first aspect of the present invention.

[0178] In 301, a first picture 21a is acquired, which is also a picture 21a of a sample 23 in a first sample configuration of bulk material to be dosed using the dosing device 1. To this end, the data of the picture 21a are received, for example, via a data line or retrieved from a memory.

[0179] In 303, the image data is processed by a first evaluation module. The first evaluation module is more specifically a machine learning model (ML model) that has learned bulk material properties from a large number of images of different bulk materials with associated properties during training. (The images used for training here each show a bulk material in a position such as Figure 2a The sample of the described sample configuration, including a correspondingly placed reference object 29, is thus obtained. The acquired image data is thus supplied to a first evaluation module and, thereby, to an ML model, which is calculated on the image data. Output data representing a first property of the bulk material is then obtained at the output of the ML model. In this case, this is a material property of the bulk material.

[0180] At 305 , a data set representing a second property of the bulk material is acquired via user input. In this case, it is another material property of the bulk material. Furthermore, a dosing parameter may optionally be acquired, also via user input, for example. For example, a minimum required delivery intensity for a planned application scenario may be predefined as a dosing parameter.

[0181] In 307, the first characteristic, the second characteristic and also the quantitative allocation parameter are processed by means of recommendation module, to find out the type of quantitative allocation device and the configuration of the bulk material of quantitative allocation device for sample.Recommendation module is exactly machine learning model (ML model), and it has learned the configuration of quantitative allocation device according to the first characteristic, the second characteristic and many different combinations of quantitative allocation parameter together with the associated configuration of quantitative allocation device within the scope of training.Therefore, data (i.e. the first characteristic, the second characteristic and also the quantitative allocation parameter) are supplied to recommendation module and supplied to ML model thus, and ML model is calculated on these data.So at the output part of ML model, obtain output data, these output data represent the type and the configuration of quantitative allocation device.Other data can be set to the input data of ML model place equally here, although this is not necessary at present.

[0182] In 309 , the ascertained configuration is output to the user on a user interface such as a screen and / or stored in a database.

[0183] For example, the second property is a material property of the bulk material, which is not ascertained from the recorded image or possibly cannot be ascertained at all.

[0184] The configuration and type of the dosing device for the bulk material are thus ascertained based on the data of the first image 21a, the data set, and, if necessary, the dosing parameters. The data of the first image 21a are not processed directly with the data set and the dosing parameters. Instead, the first bulk material properties ascertained based on the data of the first image 21a are then processed together with the second bulk material properties and, if necessary, the dosing parameters by supplying this data as input to the ML model of the recommendation module.

[0185] Figure 6 A flowchart 400 shows a fourth embodiment of the method according to the first aspect of the present invention.

[0186] 401 and 403 are very similar to 301 and 303, but in 403 the ML model of the first evaluation module has not yet learned the bulk material properties within the scope of training (as in 303), but has learned the bulk material identifier based on a number of pictures of different bulk materials with associated identifiers. (The pictures used for training here each show a bulk material in a position similar to that described in relation to the Figure 2a The sample configuration described above includes a correspondingly placed reference object 29. The acquired image data is thus supplied to a first evaluation module and, from there, to an ML model, which is calculated on this image data. Output data is then obtained at the output of the ML model, representing an identifier for the bulk material. This is an alphanumeric string that identifies the bulk material, for example, in an ERP database.

[0187] In 405 , a first property of the bulk material, in particular a material property, is retrieved from a database based on the identifier.

[0188] At 407 (optionally similar to 305 ), a dosing parameter is obtained, for example, via user input. For example, the minimum delivery intensity required in the planned application scenario can be predefined as a dosing parameter. Alternatively, the dosing parameter can be retrieved together with the first characteristic of the bulk material from a database, where dosing parameters for the corresponding bulk material may also be stored.

[0189] In 409, the first characteristic and the quantitative allocation parameter are processed by the recommendation module to find out the configuration of the bulk material for the sample of the quantitative allocation device. The recommendation module is a machine learning model (ML model) that has learned the configuration of the quantitative allocation device according to many different combinations of the first characteristic and the quantitative allocation parameter together with the associated configuration of the quantitative allocation device within the scope of training. Therefore, data (i.e. the first characteristic and the quantitative allocation parameter) are supplied to the recommendation module and thus supplied to the ML model, and the ML model is calculated on this data. So output data is obtained at the output part of the ML model, and this output data represents the configuration of the quantitative allocation device. Other data can also be set as the input data at the ML model here, although this is not necessary at present.

[0190] In 411 , the ascertained configuration is output to the user on a user interface such as a screen and / or stored in a database.

[0191] The configuration of the dosing device 1 for the bulk material is thus determined based on the data from the first captured image 21a and the dosing parameters. The data from the first captured image 21a is not directly processed with the dosing parameters. Instead, the identifier determined based on the data from the first captured image enables the identification of the first bulk material's characteristics. These first bulk material characteristics are then processed together with the dosing parameters by supplying this data as input to the ML model of the recommendation module.

[0192] Therefore, in each of the previously described embodiments of the method according to the first aspect of the present invention, the type of the dosing device and the corresponding configuration of the dosing device can be ascertained in the following manner, that is, for example, by predefining the operating parameters in the form of the discharge mechanism and / or the maximum speed of the motor of the dosing device 1. For example, according to the ascertained configuration, the discharge mechanism can be a screw and the maximum speed can be 60 revolutions per minute.

[0193] It should be noted that the ML model also inherently learns and utilizes the associations between bulk material portions and reference objects via the reference objects 29, which can lead to better configuration suggestions. However, in alternative embodiments, reference objects may not be included in the images (i.e., those acquired in the method and used to train the corresponding ML model).

[0194] Figure 7 A flow chart 500 of a method according to the second aspect of the invention is shown. With this method, a suggestion can be obtained for a type of dosing device and a corresponding configuration of the dosing device 1 for the bulk material to be dosed.

[0195] In 501, a first photograph of a sample of bulk material in a first sample configuration is taken with a camera (e.g., from Figure 2a a first picture 21a of the bulk material) and / or a second picture of a sample of the bulk material in a second sample configuration, taken with a camera (e.g., from Figure 2b A corresponding reference object 29 can also be provided in the picture.

[0196] In 503, two pictures (in particular their image data) are provided in the method according to the first aspect of the invention and are acquired there as a first picture and / or a second picture. For example, this can be as described in reference Figures 3 to 6 The method explained.

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

[0198] With the aid of the configuration suggestions, the metering device 1 can be configured very easily in a suitable manner for the bulk material to be metered. The method provided with the image data can advantageously be carried out on a cloud server.

[0199] Figure 8 A schematic diagram of an apparatus 33 for data processing according to a third aspect of the present invention is shown.

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

[0201] Figure 9 A schematic diagram of a dosing device 35 according to a fourth aspect of the invention is shown.

[0202] The dosing device 35 may be Figure 1 The apparatus 37 for data processing according to the third aspect of the present invention (such as the apparatus 37 of FIG. Figure 8 The dosing device of the device 33) described above.

[0203] Figure 10 A schematic diagram of an apparatus 39 for data processing according to a fifth aspect of the present invention is shown.

[0204] The device 39 for data processing is a smartphone with a computer 41. The device 39 provides the operator of the metering device 1 with flexible options, for example for ascertaining a suitable configuration for the metering device 1 before the bulk material 3 to be metered is filled into the storage container 5.

[0205] To this end, the device 39 for data processing has a device that is configured to provide images captured by the camera 41 (such as the pictures 21a and / or 21b) in the method according to the first aspect of the invention in such a manner that they are acquired there as a first picture and / or a second picture.

[0206] The features disclosed in the preceding description, in the drawings and in the claims may be essential to the invention in various embodiments, both individually and in any combination.

[0207] Description of Reference Numerals

[0208] 1Quantitative distribution equipment

[0209] 3 Bulk materials

[0210] 5 Storage containers

[0211] 7 connection section

[0212] 9 receiving container

[0213] 11 Surface

[0214] 13 unloading mechanism

[0215] 15 Vertical dumping section

[0216] 17 motors

[0217] 19 weighing units

[0218] 21a, 21b photo shooting

[0219] 23 Bulk material samples

[0220] 25 bases

[0221] 27a, 27b piles

[0222] 29 reference objects

[0223] 31 bracket

[0224] 33 Equipment for data processing

[0225] 35 quantitative distribution equipment

[0226] 37 Equipment for data processing

[0227] 39 Equipment for data processing

[0228] 41 Camera

[0229] 100 Flowchart

[0230] 101 Obtaining the first shot of bulk material sample

[0231] 103 Identify the configuration of quantitative distribution equipment

[0232] 105 Output and / or store the determined configuration

[0233] 200 Flowchart

[0234] 201 Obtaining the first shot of bulk material sample

[0235] 203 Obtaining a second photograph of the bulk material sample

[0236] 205 Identify the configuration of quantitative distribution equipment

[0237] 207 Output and / or store the determined configuration

[0238] 300 Flowchart

[0239] 301 Obtain the first shot of the bulk material sample

[0240] 303 processing data of the first captured picture with a first evaluation module and obtaining first properties of the bulk material

[0241] 305 obtaining a data set and optionally obtaining dosing parameters

[0242] 307 ascertaining a configuration of the dosing device

[0243] 309 outputting and / or storing the ascertained configuration

[0244] 400 flow chart

[0245] 401 capturing a first captured picture of a sample of the bulk material

[0246] 403 processing data of the first captured picture with a first evaluation module and obtaining an identifier of the bulk material

[0247] 405 retrieving first properties of the bulk material from a database

[0248] 407 obtaining dosing parameters

[0249] 409 ascertaining a configuration of the dosing device

[0250] 411 outputting and / or storing the ascertained configuration

[0251] 500 flow chart

[0252] 501 capturing a first captured picture and / or a second captured picture of a sample of the bulk material

[0253] 503 providing a captured picture in a method according to the first aspect of the present invention

[0254] 505 obtaining a recommendation for a configuration of the dosing device

[0255] Bl, B2 width

[0256] Hl, H2 height

Claims

1. A method for providing a dosing device for a bulk material to be dosed, the method comprising acquiring at least one first photograph of at least one sample of the bulk material, and Therein, based on the data of the first photograph, at least one type of metering device and a corresponding configuration of the metering device for the bulk material are ascertained.

2. A method according to claim 1, wherein the method includes determining the type of the quantitative dispensing device and the corresponding configuration of the quantitative dispensing device for the bulk material with the help of a recommendation module, the data of the first photograph being taken into consideration when determining the type and the configuration with the help of the recommendation module, and / or determining a first identifier of the bulk material based on the data of the first photograph with the help of a first evaluation module, and wherein the first identifier is taken into consideration when determining the configuration with the help of the recommendation module. 3 . The method according to claim 2 , wherein the method comprises retrieving information about the associated bulk material from a database based on the identifier and taking this into consideration when determining the configuration with the aid of the recommendation module.

4. The method according to any one of the preceding claims, wherein the method comprises acquiring at least one data set representing a second identifier of the bulk material, wherein (i) the corresponding configuration and the type of dosing device for the bulk material are ascertained by means of the recommendation module, also based on the acquired data set, and / or (ii) the data set is taken into consideration when ascertaining the type and the corresponding configuration.

5. The method according to any one of the preceding claims, wherein the method comprises obtaining a second photograph of the sample of the bulk material, and wherein (i) the corresponding configuration and the type of metering device for the bulk material are ascertained by means of the recommendation module taking into account the data of the second picture, and / or (ii) the data of the second picture are taken into account when ascertaining the corresponding configuration and the type of metering device, Preferably, (i) the first identifier of the bulk material is ascertained based on the data of the first and second pictures by means of the first evaluation module, and / or (ii) a second identifier of the bulk material is ascertained based on the data of the first and / or second pictures by means of the second evaluation module and is taken into account when ascertaining the configuration.

6. The method according to claim 5, wherein (i) the first recording and the second recording are performed from different viewing angles, 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 preferably transferred from the first sample configuration to the second sample configuration between the two recordings; The first sample configuration and the second sample configuration are preferably two differently constructed piles of the bulk material sample, and / or at least one parameter of the environmental conditions of the bulk material sample changes between the first sample configuration and the second sample configuration, the parameter being, for example, the ambient temperature, the air humidity and / or the ambient pressure. 7 . The method according to claim 1 , wherein the method comprises acquiring dosing parameters and determining a configuration of the dosing device for the bulk material based on the dosing parameters.

8. The method according to claim 1 , wherein (i) type, configuration and status data of a metering device and / or bulk material data about the bulk material to be metered respectively with the metering device are acquired from a cloud-based computer and, in particular, taken into account in the recommendation module when determining the type and the configuration, wherein the provisionally determined configuration is verified based on the acquired configuration, status data and / or bulk material data and, if the provisionally determined configuration does not correspond to a defined quality standard, is adjusted, and / or (ii) the determined configuration is compared with, in particular, a current configuration of the metering device to be used for the metering of the bulk material, and, preferably, a control signal is generated based on the result of the comparison, which control signal is preferably supplied to the metering device and / or, in particular, an entity different from the metering device, in particular as a control and / or regulation signal.

9. The method according to claim 1 , 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: particle shape, particle size, particle size, angle of repose, discharge angle, physical properties, chemical properties, moisture content, material type, density, flow behavior, arching tendency, gushing tendency in fluidized state, lumps fraction, electrostatic accumulation, chemical instability, temperature sensitivity, airborne floatability, segregation tendency, composition of components, free flowability, agglomeration tendency, abrasiveness, corrosiveness, mechanical sensitivity, brittleness, explosiveness, flammability, dustiness, moisture, adhesion, viscosity, hygroscopic behavior, temperature, fluidization tendency, hardening tendency, radioactivity, toxicity, thixotropic behavior, putrefaction tendency, softening tendency, static electricity, presence of grease, flaking and / or stickiness; and / or (ii) the second identifier of the bulk material is a tactile material property of the bulk material or is characterized by or is at least one of the following properties of the bulk material or a measure thereof: particle shape, particle size, particle size, angle of repose, discharge angle, physical properties, chemical properties, moisture content, material type, density, flow behavior, arching tendency, gushing tendency in fluidized state, lump fraction, electrostatic accumulation, chemical instability, temperature sensitivity, floatability in air, segregation tendency, composition of components, free flowability, agglomeration tendency, abrasiveness, corrosiveness, mechanical sensitivity, brittleness, explosiveness, flammability, dustiness, humidity, adhesion, viscosity, hygroscopic behavior, temperature, fluidization tendency, hardening tendency, radioactivity, toxicity, thixotropic behavior, putrefaction tendency, softening tendency, static electricity, presence of grease, flaking and / or stickiness.

10. A method for obtaining a proposal for the configuration of a dosing device for bulk material to be dosed, the method comprising taking a first picture of the bulk material, in particular a sample in a first sample configuration and / or photographing it with a camera, and / or taking a second picture of the bulk material, in particular a sample in a second sample configuration and / or photographing it with a camera, and which is provided in the method according to any one of claims 1 to 9 and obtained there as a first picture and / or a second picture.

11. The method according to claim 10, wherein the method comprises: (i) acquiring the configuration ascertained in the method according to any one of claims 1 to 9 as a suggestion for a configuration and / or acquiring a control signal generated in the method according to any one of claims 1 to 9, (ii) in particular manually ascertaining properties of the bulk material, in particular material properties, such as tactile material properties, and providing them in the method according to any one of claims 1 to 9 and acquiring them there as a data set representing a second bulk material property, and / or (iii) at least one parameter is provided in the method according to any one of claims 1 to 9 and acquired there as a dosing parameter. 12 . A device for data processing, comprising means for carrying out the method according to claim 1 .

13. A device for data processing, in particular a smartphone, having a camera and other devices, which are configured to provide images captured using the camera in a method according to any one of claims 1 to 9, so that these images are acquired there as first pictures and / or as second pictures.

Images