Automatic process control of additive manufacturing device
Automatic process control of additive manufacturing. The system includes an additive manufacturing device for making an object and a local network computer controlling the device. At least one camera is provided with a view of a manufacturing volume of the device to generate network accessible images of the object. The computer is programmed to stop the manufacturing process when the object is defective based en the images of the object.
1. System for automated process control of an additive manufacturing device comprising:
an additive manufacturing device for making an object;
a local networked computer controlling the device;
an array of lights illuminating a manufacturing volume of the device for creating object shadows for reconstructing a profile view from the point of view of each light in the array of lights;
at least one camera with a view of the manufacturing volume of the device to generate network accessible images of the object;
a layer-by-layer verification is used to detect errors on the images of the object during a printing process, wherein layer-by-layer verification using a slicer to generate a predictive render of the object after each layer is printed;
wherein the local networked computer is programmed to stop the manufacturing process automatically identifying the object is defective based on the layer-by-layer verification of the images of the object.
2. The system of claim 1 wherein the at least one camera has a fixed view of the manufacturing volume.
3. The system of claim 1 wherein the at least one camera has a robotically controlled view of the manufacturing volume.
4. The system of claim 1 wherein the images are video streams.
5. The system of claim 1 wherein the images are static.
6. The system of claim 1 wherein the additive manufacturing device is a three-dimensional printer.
7. The system of claim 1 wherein the computer further includes a series of server-side applications executing remote algorithms.
8. The system of claim 1 further including a web-browser based control interface.
9. The system of claim 7 wherein the algorithm includes machine learning algorithms.
10. The system of claim 9 wherein the machine learning algorithms include markov, bayesian inference or artificial neural network algorithms.
11. The system of claim 1 wherein the manufacturing volume includes a calibration pattern thereon.
12. The system of claim 1 further including three-dimensional print preview to update object rendering in real time.
13. The system of claim 1 wherein the images of the object are used for layer-by-layer verification using a renderer to generate the predictive render of what the object will look like after each layer is printed.
14. The system of claim 13 wherein the renderer takes as input the same geometry (triangle mesh) as a toolpath generator.
15. The system of claim 14 wherein the renderer takes as additional input slicing parameters including layer height, infill pattern and density.
16. The system of claim 13 wherein the renderer takes as input a toolpath that is used to print the object.
17. The system of claim 14 , 15 , or 16 further including calibration image(s) of a blank print surface at a variety of heights to improve the accuracy of the render and/or to isolate the relevant sections of the images of the object from each layer.