Devices, systems, and methods for virtual bulk density sensing
AssigneeFrito-Lay North America, Inc.
InventorsSean Eichenlaub, Kevin Kaichu Lin
Life of this patent
Estimating the term…
Abstract
Devices, systems, and methods for real-time food production are disclosed. Extrusion can include including evaluating and controlling one or more production devices to produce desirable food products. Evaluation can be performed by an evaluation system including a convolutional neural network to determine a bulk density value. Control can be performed by a machine learning model on the basis of the bulk density value. Control can include determination of real-time settings for production device parameters.
Claims24
A system for producing food product, the system comprising:
- at least one food product processing device for extruding food material into food products;
- a bulk density evaluation system for analyzing image information of at least one of food material and food product to determine a bulk density value;
- and
- a control system configured to govern operation of the at least one food product processing device based on the determined bulk density value, wherein the control system comprises a machine learning model configured to determine, in real-time, at least one control parameter for the at least one food product processing device, based on the determined bulk density value, wherein the machine learning model is defined based on a simulation model comprising a physical simulation of food material within the at least one food product processing device and real world line data of the food product processing device.
A method of operating a system for producing food product including one or more food product processing devices for producing food material as food products, the method comprising:
- generating a simulation model based on a physical simulation of food material within the at least one food product extrusion device;
- defining a machine learning model based on the simulation model for governing control of the at least one food product processing device;
- evaluating image information of at least one of food material and food product to determine a bulk density value;
- operating the defined machine learning model to determine, in real-time, desired setting of at least one control parameter for the at least one food product processing device based on the determined bulk density value, wherein the machine learning model is defined based on the simulation model comprising the physical simulation of food material within the at least one food product processing device and real world line data of the food product processing device;
- and
- controlling the at least one food product processing device to have the at least one desired control parameter.
A method of operating a system for producing food product including one or more food product processing devices for processing food material as food products, the method comprising:
- evaluating image information of at least one of food material and food product to determine a bulk density value;
- defining the machine learning model based on a simulation model for governing control of the at least one food product processing device, and operating the machine learning model to determine, in real-time, desired setting of at least one control parameter for the at least one food product processing device based on the determined bulk density value, wherein the machine learning model is defined based on the simulation model comprising the physical simulation of food material within the at least one food product processing device and real world line data of the food product processing device;
- and
- controlling the at least one food product processing device to have the at least one desired control parameter.
Dependencies are inferred from the claim text.