METHOD AND DEVICE FOR INSPECTING CONTAINERS

Abstract

A method for inspecting containers, wherein the containers are transported in the form of a container mass flow by a transporter and are recorded as first measurement data by a first inspection unit and as second measurement data by a second inspection unit, wherein the first measurement data and the second measurement data are evaluated jointly by an evaluation unit using an evaluation method operating based on artificial intelligence to give output data, in order to ascertain an inspection result, such as for example a fill level, from the output data.

Claims

1. A method for inspecting containers, wherein the containers are transported with a transporter as a container mass flow and are recorded with a first inspection unit as first measurement data and with a second inspection unit as second measurement data, wherein the first measurement data and the second measurement data are evaluated together by an evaluation unit with an evaluation method working on the basis of artificial intelligence to form output data in order to determine an inspection result, for example a fill level, from the output data.

2. The method according to claim 1, wherein the evaluation method working on the basis of artificial intelligence comprises at least one method step with a deep neural network, wherein the first measurement data and the second measurement data are evaluated together with the deep neural network to determine the output data.

3. The method according to claim 1, wherein the first inspection unit and/or the second inspection unit comprises at least one camera with which the containers are recorded as the first measurement data and/or the second measurement data.

4. The method according to claim 1, wherein the second inspection unit records the containers with a measurement method that is different from that of the first inspection unit.

5. The method according to claim 4, wherein the first inspection unit comprises a first sensor and the second inspection unit comprises a different second sensor.

6. The method according to claim 1, wherein plausibility of the first measurement data and the second measurement data is checked during evaluation by the evaluation unit.

7. The method according to claim 1, wherein the first measurement data and the second measurement data are combined to form common input data for the evaluation unit, and wherein the common input data are then evaluated by the evaluation unit with the evaluation method working on the basis of artificial intelligence to form the output data.

8. The method according to claim 1, wherein the evaluation method working on the basis of artificial intelligence is trained with training data sets.

9. The method according to claim 8, wherein first training measurement data of a training container is recorded with the first inspection unit and second training measurement data of a training container is recorded with the second inspection unit and combined to form one of the training data sets.

10. The device for inspection containers for carrying out the method according to claim 1, with a transporter for transporting the containers as a container mass flow, a first inspection unit to record the containers as first measurement data, and with a second inspection unit to record the containers as second measurement data, wherein an evaluation unit is designed to evaluate the first measurement data and the second measurement data together with an evaluation method working on the basis of artificial intelligence to form output data in order to determine an inspection result, for example a fill level, from the output data.

11. The device according to claim 10, wherein the evaluation method working on the basis of artificial intelligence comprises a deep neural network in order to evaluate the first measurement data and the second measurement data together with the deep neural network.

12. The device according to claim 10, wherein the first inspection unit comprises a first sensor and the second inspection unit comprises a different second sensor.

13. The device according to claim 12, wherein the second sensor is designed to record the containers with a measurement method that is different from that of the first sensor.

Description

BRIEF DESCRIPTION OF THE FIGURES

[0039] Further features and advantages of the invention are explained subsequently in more detail with reference to the exemplary embodiments shown in the figures. Shown is:

[0040] FIG. 1 an exemplary embodiment according to the invention of a device for inspecting containers from a top view; and

[0041] FIG. 2 an exemplary embodiment according to the invention of a method for inspecting containers as a flow chart.

DETAILED DESCRIPTION

[0042] In FIG. 1, an exemplary embodiment according to the invention of a device 1 for controlling the fill level of containers 2 is presented from a top view. The device 1 is designed to carry out the method 100 described subsequently in FIG. 2.

[0043] It can be seen that the container 2 is initially transferred to the filler 7 by the infeed star wheel 7 and filled there with a filling material, for example a beverage. The filler 7 comprises, for example, a carousel with filling members arranged thereon (not shown here), which fills the container 2 with a filling material during transport. Subsequently, the containers 2 are transferred via the intermediate star wheel 10 to the closer 8, where they are provided with a closure, for example a cork, crown cap or screw cap. Thus, the filling material is protected from environmental influences and can no longer leak out the container 2.

[0044] Subsequently, the containers 2 are transferred to the conveyer 3 via the outfeed star wheel 11, which transports the containers 2 as a container mass flow to the first inspection unit 4 and the second inspection unit 5. Checking the fill level of the containers 2 is only shown as an example. The transporter 3 is designed here, for example, as a conveyor belt on which the containers 2 are transported in an upright position.

[0045] The first inspection unit 4 arranged thereon comprises a first sensor 41, 42 with the lighting device 42 as sender and the camera 41 as receiver in order to record the containers 2 in transmitted light. This can be infrared light, for example. The lighting device 42 has a diffusing light emission disk that is backlit with several LEDs and thus forms an illuminated background image for the containers 2 from the perspective of the camera. The camera 41 then records the containers 2 as first measurement data and forwards them as digital signals to the computer system 6.

[0046] Moreover, the second inspection unit 5 can be seen with the sensor 51, 52, which works with a different measuring method than the first sensor 41, 42. For example, the sender can be an X-ray source 52 and the receiver an X-ray receiver 51. The signals of the X-ray receiver 51 are recorded as second measurement data and forwarded as digital signals to the computer system 6. When the X-ray passes through the filling material, it is attenuated differently than when it passes through air or the foam above the liquid level.

[0047] Consequently, the containers 2 are recorded with two different measuring methods so that in the subsequent evaluation, the inspection result, for example the fill level, can be determined more reliably for different beverage processing facilities, container types, varieties and/or environmental conditions.

[0048] Furthermore, the computer system 6 with the evaluation unit 61 can be seen. The computer system 6 comprises, for example, a CPU, a memory unit, an input- and output unit and a network interface. Accordingly, the evaluation unit 61 is implemented as a computer program product in the computer system 6.

[0049] The evaluation unit 61 is designed to evaluate the first measurement data and the second measurement data of the containers 2 using an evaluation method working on the basis of artificial intelligence to produce output data in order to determine an inspection result, such as the fill level, from the output data.

[0050] If the inspection result of the containers 2 is acceptable, then they are lead to the further processing steps following the inspection, for example to a palletizer. In contrast, the faulty containers 2 are discharged from the container mass flow by means of a switch for recycling or disposal.

[0051] In FIG. 2, an exemplary embodiment according the invention of a method 100 for inspecting containers 2 is shown as a flowchart. The method 100 is only described as an example with reference to the device 1 previously described with reference to FIG. 1.

[0052] First, the containers 2 are transported by the transporter 3 as a container mass flow in step 101. This is done, for example, by means of a conveyor belt or a carousel. The containers 2 are transported to the first inspection unit 4 and to the second inspection unit 5.

[0053] In the following step 102, the containers 2 are recorded as first measurement data by the inspection unit 4. For example, the first sensor with the lighting device 42 and camera 41 shines through the containers 2 and records them as image data.

[0054] Moreover, the containers 2 are recorded with a different sensor in addition to the inspection unit 5 in step 103. For example, an X-ray from the X-ray source 52 passes through the containers 2 and is recorded with the X-ray receiver 51.

[0055] Since the containers 2 are recorded with the different measurement methods of the first inspection unit 4 and the second inspection unit 5, the determination of the inspection result is especially reliable.

[0056] Subsequently, in step 104, the first measurement data and the second measurement data are evaluated together by the evaluation unit 61 with an evaluation method working on the basis of artificial intelligence to produce output data in order to determine an inspection result, for example the fill level, from the output data. For this purpose, the evaluation method comprises at least one method step with a deep neural network, for example a convolutional neural network. Thereby, the first measurement data and the second measurement data first pass through an input layer, one or more convolution layers and/or hidden layers, a pooling layer and an output layer. With the output layer, the output data, for example the fill level, is output directly as the inspection result. However, it is also conceivable that the output data is further processed with one or more further method steps to form the inspection result.

[0057] Moreover, in step 106, the first measurement data and the second measurement data are checked for plausibility. This is done, for example, by evaluating the first measurement data and the second measurement data individually with a conventional evaluation method and comparing the evaluation results obtained in this way with the output data of the evaluation method based on artificial intelligence.

[0058] If the determined inspection result is acceptable according to the following step 107, then the containers 2 are led to further treatment steps in step 108. Otherwise, the containers are discharged in step 109 for recycling or disposal.

[0059] In order to teach the evaluation method working on the basis of artificial intelligence of step 104, it is trained in advance with a variety of training data sets (step 105). The training data sets each comprise first training measurement data of a training container recorded with the first inspection unit, second training measurement data of the training container recorded by the second inspection unit and associated additional information. However, it is also conceivable that the first training measurement data and/or the second training measurement data originate from other inspection units of the same type. The additional information describes, for example, the fill level, a completely overfilled state, a completely underfilled state of the training container recorded in the first and second training measurement data and/or information on evaluability of the training measurement data. Consequently, data from the input layer in the form of the first and second training measurement data and from the output layer in the form of the associated additional information are known and the deep neural network can be trained accordingly on different beverage processing facilities, container types, varieties and/or environmental conditions. Thus, the user no longer has to extensively parametierize the evaluation for the various beverage processing facilities, container types, varieties and/or environmental conditions.

[0060] Since, in the device 1 and the method 100, the first measurement data and the second measurement data are evaluated together by the evaluation unit 61 with the evaluation method working on the basis of artificial intelligence to form the output data, the first measurement data and the second measurement data are already considered together during evaluation. The evaluation method working on the basis of artificial intelligence can therefore recognize relationships between the first measurement data and the second measurement data and thus take them into consideration during determination. In other words, information in the first and second measurement data that cannot be individually identified can also be taken into consideration. Consequently, the device 1 according to the invention and the method 100 according to the invention can work even more reliably. Moreover, the evaluation method working on the basis of artificial intelligence can be trained in advance for various beverage processing facilities, containers types, varieties and/or environmental conditions, so the device 1 and the method 100 no longer have to be extensively parameterized.

[0061] It is understood that the features mentioned in the exemplary embodiments described above are not limited to these feature combinations, but that individual features or any other combination of features are also possible.