Method and system for 3D printer with deformation compensation

1 . A method for three-dimensional (3D) printing, comprising:

receiving, by a main controller, an exterior geometry of a product to be printed by a 3D printer;

generating, by the main controller, a structure that corresponds to the product and includes a plurality of unit structures therein;

printing, by the 3D printer, an object based on the structure;

capturing, by one or more cameras, at least one image of the object;

determining, by the main controller, a deviation of an exterior geometry of the object from the structure by analyzing the at least one image;

receiving, by the main controller, one or more input variables that affect post-printing deformation characteristics; and

generating, by the main controller, a compensated structure based on the deviation and the one or more input variables, wherein the compensated structure, when printed by the 3D printer, causes the printed object to deform subsequent to printing to match the exterior geometry of the product,

wherein the one or more input variables include:

one or more variables associated with at least one of a thermal property or a mechanical property of printed material; and

one or more environmental parameters including at least one of an ambient temperature, an ambient humidity, or an air circulation.

2 . The method of claim 1 , wherein the one or more cameras take 5-way images, which includes front, back, left, right, and top images of the object.

3 . The method of claim 2 , wherein the 5-way images are processed by the main controller based on a machine learning algorithm.

4 . The method of claim 3 , wherein the machine learning algorithm is based on at least one of a convolutional neural network (CNN) or a recurrent neural network (RNN).

5 . The method of claim 1 , wherein the one or more environmental parameters are monitored at least intermittently.

6 . The method of claim 5 , wherein the one or more environmental parameters are monitored at regular intervals.

7 . The method of claim 1 , wherein the compensated structure is generated based on the deviation between the printed object and the generated structure, which is detected using the one or more cameras, by compensating for impacts of the one or more input variables.

8 . A non-transitory computer readable medium containing program instructions executed by a processor or controller, the program instructions when executed by the processor or controller configured to:

receive an exterior geometry of a product to be printed by a three-dimensional (3D) printer;

generate a structure that corresponds to the product and includes a plurality of unit structures therein;

cause the 3D printer to print an object based on the structure;

cause one or more cameras to capture at least one image of the object;

determine a deviation of an exterior geometry of the object from the structure by analyzing the at least one image;

receive one or more input variables that affect post-printing deformation characteristics; and

generate a compensated structure based on the deviation and the one or more input variables, wherein the compensated structure, when printed by the 3D printer, causes the printed object to deform subsequent to printing to match the exterior geometry of the product,

wherein the one or more input variables include:

one or more variables associated with at least one of a thermal property or a mechanical property of printed material; and

one or more environmental parameters including at least one of an ambient temperature, an ambient humidity, or an air circulation.

9 . The non-transitory computer-readable medium of claim 8 , wherein the one or more cameras take 5-way images, which includes front, back, left, right, and top images of the object.

10 . The non-transitory computer-readable medium of claim 9 , wherein the 5-way images are processed by the main controller based on a machine learning algorithm.

11 . The non-transitory computer-readable medium of claim 10 , wherein the machine learning algorithm is based on at least one of a convolutional neural network (CNN) or a recurrent neural network (RNN).

12 . The non-transitory computer-readable medium of claim 9 , wherein the one or more environmental parameters are monitored at least intermittently.

13 . The non-transitory computer-readable medium of claim 12 , wherein the one or more environmental parameters are monitored at regular intervals.

14 . The non-transitory computer-readable medium of claim 9 , wherein the compensated structure is generated based on the deviation between the printed object and the generated structure, which is detected using the one or more cameras, by compensating for impacts of the one or more input variables.

15 . A three-dimensional (3D) printing system, comprising:

a printing nozzle;

a main controller configured to:

receive an exterior geometry of a product to be printed with the printing nozzle;

generate a structure that corresponds to the product and includes a plurality of unit structures therein; and

cause an object to be printed with the printing nozzle based on the structure; and

one or more cameras that capture at least one image of the object,

wherein the main controller is further configured to:

determine a deviation of an exterior geometry of the object deviates from the structure by analyzing the at least one image captured by the one or more cameras; and

receive one or more input variables that affect post-printing deformation characteristics; and

generate a compensated structure based on the deviation and the one or more input variables, wherein the compensated structure, when printed by the 3D printer, causes the printed object to deform subsequent to printing to match the exterior geometry of the product, and

wherein the one or more input variables include:

one or more variables associated with at least one of a thermal property or a mechanical property of printed material; and

one or more environmental parameters including at least one of an ambient temperature, an ambient humidity, or an air circulation.

16 . The 3D printing system of claim 15 , wherein the one or more cameras take 5-way images, which includes front, back, left, right, and top images of the object.

17 . The 3D printing system of claim 16 , wherein the 5-way images are processed by the main controller based on a machine learning algorithm.

18 . The 3D printing system of claim 17 , wherein the machine learning algorithm is based on at least one of a convolutional neural network (CNN) or a recurrent neural network (RNN).

19 . The 3D printing system of claim 15 , wherein the one or more environmental parameters are monitored at least intermittently.

20 . The 3D printing system of claim 19 , wherein the one or more environmental parameters are monitored at regular intervals.