Search

Aiming at the problems of less study sample, large network scale and long training time existing in current fault diagnosis field, we develop a new method based on KPCA and selective neural network ensemble. First, reducing the data size by using KPCA to extract the sample features. Then achieving a selective neural network ensemble method based on improved binary particle swarm optimization algorithm (IBPSOSEN), and combining the two methods for fault diagnosis. In selective neural network algorithm, bagging method is used to take a number of different training sets of fault samples to solve the problem of less fault samples. Finally, simulation experiments and comparisons over Tennessee Eastman Process (TE) demonstrate the effectiveness and feasibility of the proposed method.

This paper studies the waste heat utilization device for the coal gangue brick tunnel kiln. The heat transfer mode of the waste heat utilization device is different form the past. It recovers the physical sensible heat of the high-temperature brick. This paper builds a theoretical model to analyze the situations of the cooling section of the coal gangue brick tunnel kiln, and analyzes the temperature field numerically. The results show that the distance form the waste heat utilization device to the sintering section of the coal gangue brick tunnel kiln must be more than 2m.

Explosion suppression by water mist is a new technology for the control of coal mine gas explosion with the three elements in the gas explosion at the same time. By building the physical model of the horizontal laneway in mine, and using the method of theoretical research and numerical simulation, this paper studies the relationship between the number of nozzles and H2O percentage and the distance for stable percentage of H2O, and provides a reliable for the design of water mist system for gas explosion suppression in the horizontal laneway in mine.