Heat treatment monitoring system

Abstract

A heat treatment monitoring system comprises a sensor unit having at least one sensor to determine current sensor data of food being heated; a processing unit to determine current feature data from the current sensor data; and a monitoring unit adapted to determine a current heating process state in a current heating process of the monitored food by comparing the current feature data with reference feature data of a reference heating process.

1 - 16 . (canceled) 
     
     
         17 . A heat treatment system for heating a food item, comprising:
 one or more sensors arranged to output raw sensor data; and   a computer, the computer comprising a processor and a memory, the memory storing instructions executable by the processor, the instructions including instructions such that the computer is programmed to:
 classify a type of the food item; 
 extract, from the raw sensor data, based on a type of the food item, a first subset of sensor data including values of a first feature of the sensor data, and a second subset of sensor data including values of a second feature of the sensor data, wherein the first feature and the second feature are different from one another; 
 select reference data based on the type of the food item; and 
 control heating of the food item by comparing the first and second subsets of sensor data to the reference data. 
   
     
     
         18 . The system of  claim 17 , wherein the instructions further include instructions to select one or more third subsets of sensor data from the raw sensor data, wherein each of the one or more third subsets are different from one another and from the first and second subsets of sensor data. 
     
     
         19 . The system of  claim 17 , wherein the one or more sensors includes one or more image sensors. 
     
     
         20 . The system of  claim 17 , wherein the one or more image sensors include at least one of a 3D camera, a stereo camera, or a radar. 
     
     
         21 . The system of  claim 17 , wherein the first feature and the second feature include at least one of a pixel color intensity, a pixel color distribution, and a volume represented by pixels of a specified intensity. 
     
     
         22 . The system of  claim 17 , wherein the one or more sensors is a plurality of sensors and the raw sensor data includes data from different sensor types, wherein the different sensor types include two or more of: a hygrometer, an insertion temperature sensor, a treatment chamber temperature sensor, an acoustic sensor, a scale, a timer, a camera, an image sensor, an array of photodiodes, or a gas analyzer. 
     
     
         23 . The system of  claim 17 , wherein the instructions further include instructions to classify the type of food item based on the raw sensor data. 
     
     
         24 . The system of  claim 17 , wherein the instructions further include instructions to classify the type of the food item based on user input. 
     
     
         25 . The system of  claim 17 , wherein the type of the food item includes a size of the food item. 
     
     
         26 . The system of  claim 17 , wherein the instructions further include instructions to determine a remaining time for heating the food item. 
     
     
         27 . The system of  claim 26 , wherein the remaining time is determined based on determining distances in an observation space of the subsets of sensor data and the reference data. 
     
     
         28 . The system of  claim 27 , wherein the raw sensor data includes observed temperatures and the reference data includes reference temperatures. 
     
     
         29 . The system of  claim 27 , wherein the remaining time is determined based on the reference data representing an end of heating the food item. 
     
     
         30 . The system of  claim 17 , the instructions further comprising instructions to apply a mapping to the first sensor data and the second sensor data that is derived by a variance analysis that reduces a dimensionality of the first and second subsets of sensor data. 
     
     
         31 . The system of  claim 30 , wherein the variance analysis includes applying a highest weight to subsets of sensor data having a highest variance. 
     
     
         32 . The system of  claim 17 , wherein the reference data is obtained by training a machine learning program for the type of food item at specified times, and respective temperatures at the specified times, of heating the food item. 
     
     
         33 . The system of  claim 17 , the instructions further comprising instructions to select reference data based on at least one of environmental data or a geographic location of the heat treatment system in addition to selecting the reference data based on the type of the food item. 
     
     
         34 . The system of  claim 17 , wherein controlling heating of the food item includes applying a confidence factor to the reference data.