Systems and methods for smart boiling control

1 . A method for smart boiling analysis, the method comprising:

receiving a set of one or more boiling images;

identifying a set of bubble characteristics from the set of boiling images using a first image-based model;

identifying a set of image features from the set of boiling images using a second image-based model;

predicting a set of boiling heat characteristics based on a combination of the identified set of bubble characteristics and the identified set of image features; and

controlling a flow boiling system based on the predicted set of boiling heat characteristics.

2 . The method of claim 1 , wherein the set of bubble characteristics comprises at least one of the set consisting of bubble size and bubble count.

3 . The method of claim 1 , wherein the first model comprises a Mask R-CNN model and a multilayer perceptron (MLP) model.

4 . The method of claim 1 , wherein the second model comprises a convolutional neural network (CNN), wherein the set of image features comprises features identified at a set of one or more layers of the CNN.

5 . The method of claim 1 , wherein the set of boiling heat characteristics comprises at least one of the set consisting of critical heat flux (CHF) and heat transfer coefficient (HTC).

6 . The method of claim 1 , wherein controlling the flow boiling system comprises:

determining a target flow rate to achieve a desired set of boiling heat characteristics in the flow boiling system; and

communicating with the flow boiling system to achieve the target flow rate.

7 . A non-transitory machine readable medium containing processor instructions for smart boiling analysis, where execution of the instructions by a processor causes the processor to perform a process that comprises:

receiving a set of one or more boiling images;

identifying a set of bubble characteristics from the set of boiling images using a first image-based model;

identifying a set of image features from the set of boiling images using a second image-based model;

predicting a set of boiling heat characteristics based on a combination of the identified set of bubble characteristics and the identified set of image features; and

controlling a flow boiling system based on the predicted set of boiling heat characteristics.

8 . The non-transitory machine readable medium of claim 7 , wherein the set of bubble characteristics comprises at least one of the set consisting of bubble size and bubble count.

9 . The non-transitory machine readable medium of claim 7 , wherein the first model comprises a Mask R-CNN model and a multilayer perceptron (MLP) model.

10 . The non-transitory machine readable medium of claim 7 , wherein the second model comprises a convolutional neural network (CNN), wherein the set of image features comprises features identified at a set of one or more layers of the CNN.

11 . The non-transitory machine readable medium of claim 7 , wherein the set of boiling heat characteristics comprises at least one of the set consisting of critical heat flux (CHF) and heat transfer coefficient (HTC).

12 . The non-transitory machine readable medium of claim 7 , wherein controlling the flow boiling system comprises:

determining a target flow rate to achieve a desired set of boiling heat characteristics in the flow boiling system; and

communicating with the flow boiling system to achieve the target flow rate.

13 . A smart boiling analysis system comprising:

a set of one or more processors; and

a memory connected to the set of processors, the memory storing instructions executable by the set of processors to:

receive a set of one or more boiling images from an imaging system;

identify a set of bubble characteristics from the set of boiling images using a first image-based model;

identify a set of image features from the set of boiling images using a second image-based model;

predict a set of boiling heat characteristics based on a combination of the identified set of bubble characteristics and the identified set of image features; and

control a flow boiling system based on the predicted set of boiling heat characteristics.

14 . The smart boiling analysis system of claim 13 , wherein the set of bubble characteristics comprises at least one of the set consisting of bubble size and bubble count.

15 . The smart boiling analysis system of claim 13 , wherein the first model comprises a Mask R-CNN model and a multilayer perceptron (MLP) model.

16 . The smart boiling analysis system of claim 13 , wherein the second model comprises a convolutional neural network (CNN), wherein the set of image features comprises features identified at a set of one or more layers of the CNN.

17 . The smart boiling analysis system of claim 13 , wherein the set of boiling heat characteristics comprises at least one of the set consisting of critical heat flux (CHF) and heat transfer coefficient (HTC).

18 . The smart boiling analysis system of claim 13 , wherein the instructions executable by the set of processors to control the flow boiling system comprise instructions to:

determine a target flow rate to achieve a desired set of boiling heat characteristics in the flow boiling system; and

communicate with the flow boiling system to achieve the target flow rate.