Method for regulating the addition of a flocculant to a sludge
AssigneeAndritz Inc.
InventorsAlexander Tanzer, Christoph Spielmann
Life of this patent
Estimating the term…
Abstract
The invention relates to a method for controlling the addition of a flocculant to a sludge, wherein the sludge is dewatered and images are made of the dewatered sludge and/or the dewatered liquid with a camera system. It is characterised in that the images are evaluated with a computer-implemented computational model that has previously been trained with a training data set, whereby the computational model divides the images into sub-images, classifies them and thus assesses the dewatering of the sludge. Optimal dewatering is achieved with improved ecological and economic efficiency.
Claims20
A method for controlling addition of a flocculant to a sludge, wherein
- the flocculant is added to the sludge and the sludge is subsequently at least partially dewatered in a dewatering device (1),
- individual images (2) of the dewatered sludge or the liquid dewatered from the sludge are produced with a camera system and thereafter evaluated with a computer-implemented computational model for image analysis, the computer-implemented computational model being previously trained with a training data set comprising individual training images of dewatered sludge or liquid dewatered from the sludge, wherein:
- the computer-implemented computational model for image analysis is formed as artificial neural network;
- the training data set further comprises training sub-images (3) formed from individual training images by a subdivision and classification of the individual training sub-images (3),
- a size of the training sub-images (3) is reduced from an original size for subdividing the training images,
- the size of the training sub-images (3) is selected at least large enough that the training sub-images (3) allow conclusions to be drawn about the surface texture of the dewatered sludge or liquid dewatered from the sludge,
- the computational model divides the individual images (2) into sub-images (3) analogously to the subdivision of the training images into training sub-images, comprising:
- classifying the sub-images (3) of the individual image (2), using the computational model to classify the sub-images (3) of the dewatered sludge according to a surface texture of the dewatered sludge,
- assessing the dewatering of the sludge on the basis of the classification of the sub-images (3), and
- controlling the flocculant dosage on the basis of the assessment of the dewatering of the sludge.
Dependencies are inferred from the claim text.