Container treatment machine and method for monitoring the operation of a container treatment machine

1 . A container treatment machine for treating containers in the beverage processing industry, medical technology, or cosmetics industry, the container treatment machine, comprising:

a control unit for controlling operation of the container treatment machine and at least one treatment unit for treating the containers, the container treatment machine being configured to treat the containers in exactly one way;

wherein the container treatment machine comprises:

at least one component including a sensor, wherein the sensor collects and outputs data to the control unit relating to its operating state and/or the operating state of the container treatment machine;

wherein the control unit comprises:

a neural network configured and trained to determine, on the basis of the data, whether a deviation of the operating state of the container treatment machine from a normal state is present and/or imminent,

wherein the neural network is specifically configured for the exactly one way of treating containers,

wherein the neural network is trained on a pattern of a parameter of the at least one component over an entire process cycle as a normal state of the container treatment machine,

wherein the neural network is configured in such a way that it improves parameters stored in a memory during operation of the container treatment machine such that a detected normal operation and/or a detected malfunction and/or a detected imminent malfunction are incorporated in the parameters characteristic of a pattern recognition of a normal operation, and/or a corresponding pattern recognition of an imminent and/or already occurred malfunction, during operation; and

wherein the control unit is configured to output information to an operator when the neural network determines that a deviation of the operating state of the container treatment machine from the normal state is present and/or imminent, and wherein operation of the container treatment machine is stopped based on the deviation.

2 . The container treatment machine according to claim 1 , wherein the component further comprises at least one of an encoder, a camera, a container guide, a component of the control unit, a component of the network architecture of the container treatment machine, and a servo motor, and wherein the component is configured to transmit the data to the control unit in real time.

3 . The container treatment machine according to claim 1 , wherein the neural network is a pre-learned neural network.

4 . The container treatment machine according to claim 1 , wherein the control unit is configured to feed data to the neural network during operation of the container treatment machine only, with the data having been obtained from the component or components of the container treatment machine.

5 . The container treatment machine according to claim 1 , wherein the container treatment machine is configured as one of an inspection machine, a direct printing machine, a labeling machine, a filler, a closer, a packer, a blow molding machine, a container cleaning machine, a mold filling machine, a pretreatment machine.

6 . The container treatment machine according to claim 1 , wherein the information outputted to the operator differs depending on whether the deviation of the operating state of the container treatment machine from the normal state is imminent or already present.

7 . The container treatment machine according to claim 1 , wherein the information outputted to the operator is outputted to one of a display device of the control unit and a mobile terminal communicatively coupled to the control unit.

8 . The container treatment machine according to claim 1 , wherein the information outputted to the operator is outputted one or more of visually, acoustically, and haptically.

9 . The container treatment machine according to claim 1 , wherein the component is a servo motor and the parameter is a torque existing at the servo motor.

10 . The container treatment machine according to claim 1 , wherein prior to being transmitted to the control unit, the data of the at least one component is pre-processed, where pre-processing the data includes one of altering a structure of the data, implementing suitable security mechanisms, and making a modification of neural network parameters immediately available.

11 . A method, comprising:

monitoring the operation of a container treatment machine for treating containers in the beverage processing industry, medical technology, or cosmetics industry, wherein the container treatment machine comprises:

a control unit controlling the operation of the container treatment machine and at least one treatment unit treating containers,

wherein the container treatment machine treats containers in exactly one way,

wherein the container treatment machine comprises at least one component including a sensor, wherein the sensor collects and outputs data to the control unit data-relating to its operating state and/or the operating state of the container treatment machine,

wherein the control unit comprises a neural network configured and trained to determine, based on the data, whether a deviation of the operating state of the container treatment machine from a normal state is present and/or imminent,

wherein the neural network is specifically configured for the exactly one way of treating containers, wherein the neural network is trained on a pattern of a parameter of the at least one component over an entire process cycle as a normal state of the container treatment machine,

wherein the neural network is configured in such a way that it improves parameters stored in a memory during operation of the container treatment machine such that a detected normal operation and/or a detected malfunction and/or a detected imminent malfunction are incorporated in the parameters characteristic of a pattern recognition of a normal operation, and/or a corresponding pattern recognition of an imminent and/or already occurred malfunction, during operation,

wherein the control unit outputs information to an operator when the neural network determines that a deviation of the operating state of the container treatment machine from the normal state is present and/or imminent,

wherein the at least one component is configured to transmit data to the control unit in real time, and

wherein operation of the container treatment machine is stopped based on the deviation.

12 . The method according to claim 11 , wherein the neural network is a deep neural network (DNN).

13 . The method according to claim 11 , wherein for learning during operation of the container treatment machine the control unit forwards to the neural network data from the component or components of the container treatment machine only.

14 . The method according to claim 11 , wherein the control unit transmits additional data to the neural network during maintenance of the container treatment machine and the neural network learns from the additional data.

15 . The method according to claim 14 , wherein the additional data comprises data about an operating state of at least one other container treatment machine of a container treatment system, to which the container treatment machine belongs; and/or wherein the additional data comprises data about an operating state of a container treatment machine of the same type.

16 . The method according to claim 11 , wherein the component comprises at least one of a sensor, an encoder, a camera, a container guide, a component of the control unit, a component of the network architecture of the container treatment machine, and a servo motor.

17 . The method according to claim 11 , wherein the control unit outputs information to an operator when the neural network determines that a deviation of the operating state of the container treatment machine from a normal state is present and/or imminent.

18 . A container treatment machine for treating containers in the beverage processing industry, medical technology, or cosmetics industry, the container treatment machine comprising:

a control unit for controlling operation of the container treatment machine; and

at least one treatment unit for treating the containers, the container treatment machine being configured to treat the containers in exactly one way,

wherein the container treatment machine comprises at least one component that can including a sensor, wherein the sensor collects and outputs data to the control unit relating to its operating state and/or the operating state of the container treatment machine,

wherein the control unit comprises a neural network configured and trained to determine, on the basis of the data, whether a deviation of the operating state of the container treatment machine from a normal state is present and/or imminent,

wherein the neural network is specifically configured for the exactly one way of treating containers, wherein the control unit is configured to output information to an operator when the neural network determines that a deviation of the operating state of the container treatment machine from a normal state is present and/or imminent,

wherein the neural network is configured to learn from an operation of the container treatment machine,

wherein the neural network is configured in such a way that it improves parameters stored in a memory during operation of the container treatment machine such that a detected normal operation and/or a detected malfunction and/or a detected imminent malfunction are incorporated in the parameters characteristic of a pattern recognition of a normal operation, and/or a corresponding pattern recognition of an imminent and/or already occurred malfunction, during operation,

wherein the control unit is configured to output information to an operator when the neural network determines that a deviation of the operating state of the container treatment machine from a normal state is present and/or imminent,

wherein the component comprises at least one of a sensor, an encoder, a camera, a container guide, a component of the control unit, a servo motor, a component of the network architecture of the container treatment machine,

wherein the component transmits the data in real time to the control unit, and

wherein operation of the container treatment machine is stopped based on the deviation.