This article presents a fast and uncomplicated method to modify multilayer perceptrons allowing for a considerable single-step reduction of the cost function which in this case is the mean of squared errors. The method consists in, but is not limited to the change of neuron activation functions in the last hidden layer and in the single application of the least squares method. No changes are made to neuron weights in any hidden layer. Some essential strong points of the method lie in the fact that it can be used to improve operation of networks trained earlier and the learning process need not be started from the very beginning.

No abstract

The use of low-emission combustion techniques in pulverized coal-fired (PC) boilers are usually associated with the formation of a reduced-gas atmosphere near evaporator walls. This increases the risk of high temperature (low oxygen) corrosion processes in coal-fired boilers. The identification of the dynamics and the locations of these processes, and minimizing negative consequences are essential for power plant operation. This paper presents the diagnostic system for determining corrosion risks, based on continuous measurements of flue gas composition in the boundary layer of the combustion chamber, and artificial intelligence techniques. Experience from the implementation of these measurements on the OP-230 hard coal-fired boiler, to identify the corrosion hazard of one of the evaporator walls, has been thoroughly described. The results obtained indicate that the continuous controlling of the concentrations of O2 and CO near the water wall, in combination with the use of neural networks, allows for the forecasting of the corrosion rate of the evaporator. The correlation between flue gas composition and corrosion rate has been demonstrated. At the same time, the analysis of the possibilities of significantly simplifying the measurement system by using neural networks was carried out.

Congestion extends the time of the journey for both people and goods. Therefore, transport solutions should be optimized. Management scientists and technical scientists worked together in order to develop a proprietary solution to increase efficiency in terms of productivity improvements for intelligent transport systems. The most fundamental functions of management have been paired with a detailed analysis of city traffic. The authors developed a method for determining the order of vehicles at traffic lights and connected it with vehicle-to-vehicle communication and GPS signals. As a result, a novel method to increase the throughput of intersections is presented. This solution generates a sound signal in order to inform the driver that the preceding car has started moving forward. The proposed solution leads to the shortening of the reaction time of the drivers waiting in a queue. This situation is most common at red lights. Consequently, the traffic simulation shows that the discharge of queues at traffic lights may be quicker by up to 13.5%. Notably, that proposed solution does not require any modification of the infrastructure as well as any additional devices for vehicle-to-infrastructure communication at the road intersections. To conclude, proper implementation of the proposed solution will certainly contribute to efficiency improvements within intelligent transport systems, with the potential to reduce traffic jams.