# US 12,759,239 B2 · Triangulation-based anomaly detection in three dimensional printers

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,759,239 B2
- Document ID: US12759239B2
- Status: Granted
- Kind: B2
- Application number: 18/282,878
- Filed: 2021-03-24
- Published: 2024-05-16
- Granted: 2026-10-13
- Earliest claimed: 2021-03-24
- Assignees: Peridot Print LLC
- Applicants: Peridot Print LLC
- Inventors: Prakash Reddy; Prateek Kumar Sikdar; Amit Kumar; Manivannan Srinivasan
- Web page: https://patentgrep.com/patent/US12759239B2

## CPC

- B29C 64/393: for controlling or regulating additive manufacturing processes
- G06T 7/0004: {Industrial image inspection}
- B33Y 50/02: for controlling or regulating additive manufacturing processes
- B29C: SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING (making preforms B29B11/00; making laminated products by combining previously unconnected layers which become one product whose layers will remain together B32B37/00 - B32B41/00)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- B33Y: ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING

## Abstract

Examples of systems for triangulation-based detection of anomaly in a print job performed by a three-dimensional printer are described herein. In an example, a data pertaining to a set of layers printed based on the print job of the 3D printer may be provided to two models to obtain respective predicted anomalies. Thereafter, the obtained predicted anomalies may be triangulated to detect an anomaly in the layer being printed by the 3D printer.

## Claims

### Claim 1

A method comprising:
providing, by a processor, a data set pertaining to a sequence of layers that have been printed by a 3D printer in a print job for one or more objects, for interpretation by a first machine learning model and a second machine learning model;
providing, by the processor, real-time data of a current layer being printed by the 3D printer, which is subsequent to the sequence of layers that have been printed, to the first machine learning model and the second machine learning model;
based on the interpretation and the real-time data, obtaining, by the processor, a first predicted anomaly and a second predicted anomaly for the current layer being printed, from the first machine learning model and the second machine learning model, respectively;
detecting an anomaly in the current layer being printed based on triangulation of the first predicted anomaly and the second predicted anomaly; and
after detecting the anomaly in the current layer, either terminating the print job to lessen build material wastage, or adjusting printing of the print job to minimize quality degradation of the objects.

### Claim 2 (depends on 1)

The method of claim 1, wherein the first machine learning model is an encoder-decoder based deep learning model and the second machine learning model is a time-series decomposition model.

### Claim 3 (depends on 2)

The method of claim 2, wherein the encoder-decoder based deep learning model comprises long short-term memory (LSTM) units to generate a summary of a sequence of the data set obtained for the sequence of layers.

### Claim 4 (depends on 1)

The method of claim 1, wherein the detected anomaly is categorized as one of a ghost layer anomaly, layer phase shifting anomaly, and a crazing anomaly.

### Claim 5 (depends on 1)

The method of claim 1, further comprising generating, by the processor in real-time and in response to detecting the anomaly, a notification informing degradation in a layer quality associated with the print job of the 3D printer to a user.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
training the first machine learning model and the second machine learning model about a normal printing behavior of the 3D printer based on data sets pertaining to multiple sequences of printed layers; and
storing a first trained machine learning model and a second trained machine learning model in a database.

### Claim 7 (depends on 1)

The method of claim 1, wherein, after detecting the anomaly in the current layer, the print job is terminated.

### Claim 8 (depends on 1)

The method of claim 1, wherein, after detecting the anomaly in the current layer, printing of the print job is adjusted.

### Claim 9

A non-transitory machine-readable medium storing instructions executable by a processor to perform processing comprising:
providing a data set pertaining to a sequence of layers that have been printed by a 3D printer in a print job for one or more objects, for interpretation by a first machine learning model and a second machine learning model;
providing real-time data of a current layer being printed by the 3D printer, which is subsequent to the sequence of layers that have been printed, to the first machine learning model and the second machine learning model;
based on the interpretation and the real-time data, obtaining a first predicted anomaly and a second predicted anomaly for the current layer being printed, from the first machine learning model and the second machine learning model, respectively;
detecting an anomaly in the current layer being printed based on triangulation of the first predicted anomaly and the second predicted anomaly; and
in response to detecting the anomaly in the current layer, either terminating the print job to lessen build material wastage, or adjusting printing of the print job to minimize quality degradation of the objects.

### Claim 10 (depends on 9)

The non-transitory machine-readable medium of claim 9, wherein the first machine learning model is an encoder-decoder based deep learning model and the second machine learning model is a time-series decomposition model.

### Claim 11 (depends on 10)

The non-transitory machine-readable medium of claim 10, wherein the encoder-decoder based deep learning model comprises long short-term memory (LSTM) units to generate a summary of a sequence of the data set obtained for the sequence of layers.

### Claim 12 (depends on 9)

The non-transitory machine-readable medium of claim 9, wherein the detected anomaly is categorized as one of a ghost layer anomaly, layer phase shifting anomaly, and a crazing anomaly.

### Claim 13 (depends on 9)

The non-transitory machine-readable medium of claim 9, wherein, in response to detecting the anomaly in the current layer, the print job is terminated.

### Claim 14 (depends on 9)

The non-transitory machine-readable medium of claim 9, wherein, in response to detecting the anomaly in the current layer, printing of the print job is adjusted.

### Claim 15

A system comprising:
a processor; and
a memory storing instructions executable by the processor to perform processing comprising:
providing a data set pertaining to a sequence of layers that have been printed by a 3D printer in a print job for one or more objects, for interpretation by a first machine learning model and a second machine learning model;
providing real-time data of a current layer being printed by the 3D printer, which is subsequent to the sequence of layers that have been printed, to the first machine learning model and the second machine learning model;
based on the interpretation and the real-time data, obtaining a first predicted anomaly and a second predicted anomaly for the current layer being printed, from the first machine learning model and the second machine learning model, respectively;
detecting an anomaly in the current layer being printed based on triangulation of the first predicted anomaly and the second predicted anomaly; and
in response to detecting the anomaly in the current layer, either terminating the print job to lessen build material wastage, or adjusting printing of the print job to minimize quality degradation of the objects.

### Claim 16 (depends on 15)

The system of claim 15, wherein the detected anomaly is categorized as one of a ghost layer anomaly, layer phase shifting anomaly, and a crazing anomaly.

### Claim 17 (depends on 15)

The system of claim 15, wherein, in response to detecting the anomaly in the current layer, the print job is terminated.

### Claim 18 (depends on 15)

The system of claim 15, wherein, in response to detecting the anomaly in the current layer, printing of the print job is adjusted.

### Claim 19 (depends on 15)

The system of claim 15, further comprising the 3D printer.