Method and system for controlling tube orientation in a food packaging system

A food packaging machine comprising:

• a plurality of sub-systems configured for managing a tube orientation;
• a memory;
• and
• a processor,
• wherein the memory stores instructions that, when executed by the processor, cause the processor to perform a method comprising:
• receiving one or more variable values associated with a quality of a tube orientation of a first food package, the one or more variable values indicating measurements by the food packaging machine of one or more physical parameters in one or more of sub-systems of the plurality of sub-systems, the one or more physical parameters affecting the tube orientation of the first food package;
• determining one or more control parameter values for the one or more of the sub-systems by processing the one or more variable values associated with the quality of the tube orientation of the first food package using a reinforcement learning model and a local control model, wherein determining the one or more control parameter values comprises:
• processing the one or more variable values associated with the quality of the tube orientation of the first food package using the local control model to determine whether the quality of the tube orientation of the first food package meets a target quality;
• at a first time, in response to the target quality being met, receiving a positive reward associated with the one or more variable values associated with the quality of the tube orientation of the first food package to train the reinforcement learning model;
• at a second time, in response to the target quality not being met, receiving a negative reward associated with the one or more variable values associated with the quality of the tube orientation of the first food package to train the reinforcement learning model;
• and
• determining the one or more control parameter values based on the reinforcement learning model being trained on an accumulation of one or more positive rewards and one or more negative rewards, each associated with one or more variable values for a respective food package of a plurality of food packages;
• and
• adjusting operation of a tube formation sub-system of the one or more sub-systems in the food packaging machine in accordance with the one or more control parameter values determined for the one or more of the sub-systems to manage a tube orientation of a second food package.