Development of the intellectual complex for parallel work of steam boilers

Abstract

High rates of industrial and social progress require a sharp increase in heat generation on the basis of the powerful development of fuel and energy. Design of parallel operation of several boilers today is an important and necessary part of effective work in the workplace. Parallel connection of the boiler is made to: increase the maximum output and its subsequent progression, improve resiliency boilers, economical power consumption due to less loss of efficiency when operating at partial power, raising the living resource boilers, thrifty power consumption due to less loss of efficiency when operating at partial power, raising the living resource boilers, prevent local overheating and coking of tubes in the separation of heavy residues. Despite the significant advantages of using a parallel connection of the boiler there are problems such as a complex piping boiler, consumption of materials to connect the boiler, the increase in unforeseen expenditure. In the operation of the boiler unit therein may be damaged (piping, boiler elements accident water economizers) become unstable (water omission due to poor ventilation compartment exhaust emissions occur explosions and pops) that create dangerous situations fraught failure of the equipment or boiler unit as a whole, with the destruction of large material losses and loss of human life. A neural network is a system of contact between a simple processor whose operation is processing of received signals and send them to other CPUs. This processor is called a neuron. Artificial neural networks are selected for the development of process control systems due to the fact that they are fault tolerant. In a neural network information is distributed throughout the network, which means in case of failure of the neuron network behavior will be changed slightly, changing the behavior of neurons, but the network itself continues to operate successfully. Neural networks are not programmed in the usual sense of the word, they are trained. The possibility of training - one of the major advantages of neural networks over conventional algorithms. Technical training is to find the coefficients of the connections between neurons. During training, the neural network is able to identify the complex relationships between input and output data, and perform synthesis. This means that in case of successful learning network will be able to return the correct result on the basis of data that were not available in the training set.