# US 2023/0266752 A1 · Container treatment machine and method for monitoring the operation of a container treatment machine > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0266752 A1 - Document ID: US20230266752A1 - Status: Published application - Kind: A1 - Application number: 17/997,350 - Filed: 2021-04-23 - Published: 2023-08-24 - Earliest claimed: 2020-04-29 - Assignees: Krones AG - Applicants: Krones AG - Inventors: Stefan PIANA; Herbert KOLB; Alexander HEWICKER; Anton NIEDERMEIER - Web page: https://patentgrep.com/patent/US20230266752A1 ## CPC - G05B 13/048: {using a predictor} - G05B 23/024: {Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks} - B65B 57/00: Automatic control, checking, warning, or safety devices (registering wrapping or container-forming material fed from rolls B65B41/18) - B67C 3/007: {Applications of control, warning or safety devices in filling machinery (flow-control B67C3/28)} - G05B 13/027: {using neural networks only} - G05B 19/41875: {characterised by quality surveillance of production} - G05B 23/0254: {based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks} - G05B 23/0283: {Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] (preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06)} - G05B 2219/34477: Fault prediction, analyzing signal trends - G05B 2219/45048: Packaging - Y02P 90/02: Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS] - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) - B65B: MACHINES, APPARATUS OR DEVICES FOR, OR METHODS OF, PACKAGING ARTICLES OR MATERIALS; UNPACKING (bundling and pressing devices for cigars A24C1/44; devices for tensioning and securing binders adapted to be supported by the article or articles to be bound B25B25/00; applying closure members to bottles, jars or similar containers B67B1/00-B67B6/00; concurrent cleaning, filling and closing of bottles B67C7/00; emptying bottles, jars, cans, casks, barrels or similar containers B67C9/00) - B67C: CLEANING, FILLING WITH LIQUIDS OR SEMILIQUIDS, OR EMPTYING, OF BOTTLES, JARS, CANS, CASKS, BARRELS, OR SIMILAR CONTAINERS, NOT OTHERWISE PROVIDED FOR; FUNNELS - Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS ## Abstract The invention relates to a container treatment machine for treating containers, in particular in the beverage-processing industry, medical technology, or the cosmetics industry, the container treatment machine comprising a control unit for controlling the function of the container treatment machine and at least one treatment unit for treating the containers; the container treatment machine is designed to treat the containers in exactly one way; the container treatment machine comprises at least one component which can output data relating to its operating state and/or the operating state of the container treatment machine to the control unit; and the control unit comprises a neural network which is configured and trained to use the data to determine whether a deviation of the operating state of the container treatment machine from a normal state is present and/or imminent. ## Claims ### Claim 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 that can output to the control unit data relating to its operating state and/or the operating state of the container treatment machine, and 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. ### Claim 2 (depends on 1) The container treatment machine according to claim 1, 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. ### Claim 3 (depends on 1) The container treatment machine according to claim 1, 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. ### Claim 4 (depends on 1) The container treatment machine according to claim 1, wherein the neural network is configured to learn from an operation of the container treatment machine. ### Claim 5 (depends on 1) The container treatment machine according to claim 1, wherein the neural network is a pre-learned neural network. ### Claim 6 (depends on 1) 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. ### Claim 7 (depends on 1) 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. ### Claim 8 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 outputting to the control unit data relating to its operating state and/or the operating state of the container treatment machine, and 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. ### Claim 9 (depends on 8) The method according to claim 8, wherein the neural network is a deep neural network. ### Claim 10 (depends on 8) The method according to claim 8, wherein the neural network learns from the operation of the container treatment machine. ### Claim 11 (depends on 10) The method according to claim 10, 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. ### Claim 12 (depends on 8) The method according to claim 8, 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. ### Claim 13 (depends on 12) The method according to claim 12, 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. ### Claim 14 (depends on 8) The method according to claim 8, 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/or wherein the component transmits the data in real time to the control unit. ### Claim 15 (depends on 8) The method according to claim 8, 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.