Nanjing University

Deyuan Dong

Hongqiang Ren

Bing Wu

Haidong Hu

Jinfeng Wang

Jin Wang

A deep learning-based method for predicting the settleability of activated sludge includes: (1) collecting a plurality of activated sludge samples, acquiring raw data of images of the plurality of activated sludge samples, cleaning the raw data of the images, and standardizing data sizes of the images; (2) calculating a sludge volume index (SVI) for each of the plurality of activated sludge samples; (3) establishing, by using a ResNet50 deep neural network, a model for predicting the settleability of activated sludge; and (4) predicting the settleability of a target activated sludge using the model established in (3).

Deep learning-based method for predicting settleability of activated sludge

A device for in-situ measuring settleability of activated sludge includes a sample chamber, an ultrasonic time domain reflectometer, a magnetic stirrer, an ultrasonic probe, a sample inlet, a sample outlet, and a stagnant zone. The sample chamber is configured to hold an activated sludge sample, and the ultrasonic time domain reflectometer is configured to measure the settling characteristics of the activated sludge. The stagnant zone is disposed in the sample chamber. The sample inlet and the sample outlet communicate with the sample chamber. The stagnant zone includes a top part, a sidewall, and a bottom part. The sample inlet is connected to the top part of the stagnant zone. The sample outlet is connected to the sidewall of the stagnant zone. The magnetic stirrer is disposed at the bottom part of the stagnant zone. The ultrasonic probe is disposed on the top part of the stagnant zone.

Growing community of inventors

Nanjing, China

Deyuan Dong