Disclosed herein are machine learning-based methods and systems for automated object defect classification and adaptive, real-time control of additive manufacturing and/or welding processes.

The invention provides a sliced image processing method including following steps: analyzing a sliced object in a sliced image to determine whether the sliced object has a first contour line segment and a nearest second contour line segment, where the second contour line segment is located within a region encircled by the first contour line segment; determining whether vector directions of the first contour line segment and the second contour line segment are opposite when the sliced object has the first contour line segment and the second contour line segment, and correcting the vector direction of at least one of the first contour line segment and the second contour line segment when the vector directions of the first contour line segment and the second contour line segment are not opposite.

Techniques for generating a support structure for an object are provided. In some embodiments, one or more regions of the object are identified as one or more regions to which mechanical support is to be provided and one or more support points within at least a first region of the one or more regions are identified. A support structure may be generated for the object that comprises one or more support tips coupled to the object at the one or more support points, where the support tips being generated based at least in part on a direction normal to the surface of the object at the respective support point. Techniques for providing visual feedback to a user relating to an amount of support that a support structure is expected to provide during fabrication are also provided.

Some aspects provide a method of generating a support structure for an object, the support structure and the object to be fabricated via one or more additive fabrication techniques, comprising identifying one or more regions of the object as one or more regions to which mechanical support is to be provided, identifying one or more support points within at least a first region of the one or more regions, and generating the support structure for the object, the support structure comprising one or more support tips coupled to the object at the one or more support points, the support tips being generated based at least in part on a direction normal to the surface of the object at the respective support point.

A system for additive metal manufacturing, including a deposition mechanism, a translation mechanism mounting the deposition mechanism to the working volume, and a stage. A method for additive metal manufacturing including: selectively depositing a material carrier within the working volume; removing an additive from the material carrier; and treating the resultant material.

A method for reversed modeling of biomedical model of the present invention comprises at least the following steps: (a) Obtaining the data of a first model; (b) Transferring data of the first model into data of a second model which are applied to a rapid Prototyping machine; (c) Entering data of the second model into the rapid prototyping machine; (d) Laying model materials, coating adhesives and continuing sterilization by the rapid prototyping machine and stacking until a biomedical model is made; wherein sterilization is done during stacking medical model, therefore keeping the biomedical model sterile inside is achieved.

A computer system for dynamically controlling printing parameters within a three-dimensional printer receives an indication for printing a target object by the three-dimensional printer. The computer system accesses a materials attribute dataset. The materials attribute dataset describes different material properties of a plurality of thermoset materials or mixtures thereof. Based upon the materials attribute dataset, for each of the plurality of extruders, the computer system selects one or more thermoset materials among the plurality of thermoset materials for each of the plurality of extruder to form an extrudate and determines an extrusion configuration for the selected one or more thermoset materials. The computer system then generates a command to cause the plurality of extruders of the thermoset three-dimensional printer to implement the extrusion configurations for the plurality of extruders while printing the target object.

Systems and methods for virtual machine management are disclosed. A virtual machine manager may communicate with a storehouse, which may include one or more virtual machines. The virtual machine manager may select one or more virtual machines, or may create one or more virtual machines, depending on the requirements of an input.

Systems for fabrication of dental appliances are provided. In some embodiments, a system includes an additive manufacturing system configured to perform operations including: fabricating a first elongate shaft having a first connection region for connecting to a shell of a dental appliance, fabricating a second elongate shaft having a second connection region for connecting to the shell or to a tooth, fabricating a first elongate connector coupled to the first and second elongate shafts, and fabricating a second elongate connector coupled to the first elongate shaft and extending toward the second elongate shaft, where the first and second elongate connectors are coupled to the first elongate shaft at respective locations separate from the first connection region, and where the first elongate connector is coupled to the second elongate shaft at a location separate from the second connection region.

Process control parameters are predicted to fabricate an object using deposition. An input design geometry is provided for the object. A training data set includes past post-build physical inspection data for a plurality of objects that comprise at least one object that is different from the object to be physically fabricated; and training data generated through a repetitive process of randomly choosing values for each of multiple process control parameters and scoring adjustments to the multiple process control parameters as leading to either undesirable or desirable outcomes, the outcomes based respectively on the presence or absence of defects detected in a fabricated object arising from the process control parameter adjustments. A machine learning algorithm is trained using the provided training data set and a predicted optimal set of the multiple process control parameters is generated for initiating and performing the deposition process to fabricate the object.