Computer-implemented, adapted anomaly detection method for powder-bed-based additive manufacturing
A computer-implemented anomaly detection method in powder-bed-based additive manufacture of a workpiece includes (i) providing an image data set and applying a Principal Component Analysis to said image data to compute a number of image clusters, (ii) applying a clustering algorithm to the analyzed image data and computing respective cluster centroids, (iii) comparing the computed cluster centroids with a set of reference anomaly centroids, wherein based on a match of cluster centroids with the reference, the image data is segmented layerwise into cluster images of a specific anomaly, (iv) transforming the segmented images into a defined color space, such as a Lab color space or greyscale spectrum, and, (v) integrating a pixel information of the transformed segmented cluster images to compute a threshold value for the image data set in order to determine a respective anomaly.
1 . A computer-implemented anomaly detection method in powder-bed-based additive manufacture of a workpieces, comprising:
(i) providing an image data set (OT) and applying a Principal Component Analysis (PCA) to analyze said image data to compute a number of image clusters (C),
(ii) applying a clustering algorithm to the analysed image data and computing respective cluster centroids (C),
(iii) comparing the computed cluster centroids (C) with a set of reference anomaly centroids, wherein, based on a match of cluster centroids with the reference anomaly centroids, the image data is segmented layerwise into segmented cluster images of a specific anomaly,
(iv) transforming the segmented cluster images into a defined color space, and
(v) integrating a pixel information of the transformed segmented cluster images to compute a threshold value for the image data set in order to determine a respective anomaly (a, t), wherein a lower and/or an upper threshold value (t up , t low ) is computed for the image data set in order to provide a threshold range for the respective anomaly.
2 . The method according to claim 1 ,
wherein the clustering algorithm comprises a K-Means Clustering, a Fuzzy C-Means Clustering, a Density-Based Spatial Clustering algorithm, or a DBSCAN.
3 . The method according to claim 1 , further comprising:
detecting a “hot spot” (HS), a “cold spot” (CS), a blob defect, an overexposed and/or an underexposed region in a powder bed during manufacture of the workpieces.
4 . The method according to claim 1 , further comprising:
constituting said image data (OT) by a stack of layered images, comprising photographic and/or optical tomography data.
5 . The method according to claim 4 ,
wherein step (i) providing the image data (OT) set comprises providing a stack of random and/or test images as a reference, which are subjected to a Principal Component Analysis (PCA) and to a clustering algorithm for computing cluster centroids (C), wherein the cluster images are selected in order to provide for a reference anomaly centroids information.
6 . The method according to claim 4 ,
wherein said image data (OT) is constituted by an input of an optical monitoring system of a powder bed fusion device, a CCD or sCMOS Camera, and said image data forms a test reference.
7 . The method according to claim 1 , further comprising:
using the computed threshold values as input parameters for a subsequent anomaly detection, thresholding or image processing method.
8 . The method according to claim 1 , further comprising:
marking an anomaly (a) in each layer (L) of the image data set and forming into anomaly clusters.
9 . The method according to claim 8 , further comprising:
determining a location and/or a size of the respective anomaly cluster with reference to the actual workpiece geometry.
10 . The method according to claim 9 , further comprising:
storing an anomaly cluster information, comprising a location, a size and/or a severity indicator of a given anomaly cluster in a report file.
11 . The method according to claim 9 , further comprising:
correlating an anomaly cluster information, comprising a location, a size and/or a severity indicator of a given anomaly cluster with real material or manufacturing defects.
12 . A method of manufacturing a workpiece out of a powder bed by selective laser sintering, selective laser melting or electron beam melting, comprising:
applying the computer-implemented anomaly detection method according to claim 1 .
13 . A data processing apparatus configured to carry out the method of claim 1 , comprising:
an interface to a powder bed fusion device or a related monitoring system.
14 . A non-transitory computer readable medium having a computer program product (CPP) stored thereon, comprising:
instructions which, when executed by a data processing apparatus or a computer, cause it to carry out the method of claim 1 .
15 . The method according to claim 1 ,
wherein the defined color space comprises a Lab (Lab) color space or greyscale (GV) spectrum.
16 . The method according to claim 8 ,
wherein the anomaly is formed into anomaly clusters by using a nearest neighbor search algorithm, a Connected Component Labeling, a Proximity or Closest Point Search, a Point Location or Point in Triangle Search or a k-Nearest Neighbor algorithm.
17 . A computer-implemented anomaly detection method in powder-bed-based additive manufacture of a workpieces, comprising:
(i) providing an image data set (OT) and applying a Principal Component Analysis (PCA) to analyze said image data to compute a number of image clusters (C),
(ii) applying a clustering algorithm to the analysed image data and computing respective cluster centroids (C),
(iii) comparing the computed cluster centroids (C) with a set of reference anomaly centroids, wherein, based on a match of cluster centroids with the reference anomaly centroids, the image data is segmented layerwise into segmented cluster images of a specific anomaly,
(iv) transforming the segmented cluster images into a defined color space, and
(v) integrating a pixel information of the transformed segmented cluster images to compute a threshold value for the image data set in order to determine a respective anomaly (a, t).