Object detection with an alkali-metal spin maser

Under certain conditions, ash in black liquor forms a locally corrosive environment in a kraft recovery boiler. The ash also might cause efficiency losses and even boiler shutdown because of plugging of the flue gas passages. The most troublesome compounds in a fuel such as black liquor are potassium and chlorine because they change the melting behavior of the ash. Fouling and corrosion of the kraft recovery boiler have been researched extensively, but few computational models have been developed to deal with the subject. This report describes a computational fluid dynamics-based method for modeling the reactions between alkali metal compounds and for the formation of fine fume particles in a kraft recovery boiler furnace. The modeling method is developed from ANSYS/FLUENT software and its Fine Particle Model extension. We used the method to examine gaseous alkali metal compound and fine fume particle distributions in a kraft recovery boiler furnace. The effect of temperature and the boiler design on these variables, for example, can be predicted with the model. We also present some preliminary results obtained with the model. When the model is developed further, it can be extended to the superheater area of the kraft recovery boiler. This will give new insight into the variables that increase or decrease fouling and corrosion

Download Full-text

Visual Odometry with Dynamic Object Detection by Complementary Integration of Optical Flows and Pattern Recognition

Proceedings of the 30th International Technical Meeting of The Satellite Division of the Institute of Navigation (ION GNSS+ 2017) ◽

10.33012/2017.15316 ◽

2017 ◽

Author(s):

Kojiro Takeyama ◽

Takashi Machida ◽

Yoshiko Kojima ◽

Nobuaki Kubo

Keyword(s):

Pattern Recognition ◽

Object Detection ◽

Visual Odometry ◽

Dynamic Object ◽

Optical Flows

Download Full-text

Automatic accounting of Baikal diatomic algae: approaches and prospects

Issues of modern algology (Вопросы современной альгологии) ◽

10.33624/2311-0147-2019-2(20)-295-299 ◽

2019 ◽

pp. 295-299

Author(s):

Кonstantin А. Elshin ◽

Еlena I. Molchanova ◽

Мarina V. Usoltseva ◽

Yelena V. Likhoshway

Keyword(s):

Object Detection ◽

Loss Function ◽

Classification Accuracy ◽

Diatom Species ◽

Bounding Box ◽

Synedra Acus ◽

And Training

Using the TensorFlow Object Detection API, an approach to identifying and registering Baikal diatom species Synedra acus subsp. radians has been tested. As a result, a set of images was formed and training was conducted. It is shown that аfter 15000 training iterations, the total value of the loss function was obtained equal to 0,04. At the same time, the classification accuracy is equal to 95%, and the accuracy of construction of the bounding box is also equal to 95%.

Download Full-text