The article deals with the problem of optimizing the operation of soot blowers in a pulverized coal-fired boiler based on the instantaneous degree of cleanliness of heating surfaces, determined in real time. The elaborated methodology of calculations and the algorithm that determines the optimal configuration of the blowers operation has been implemented and tested on a boiler with a capacity of 380 t/h. The indicator defining the degree of cleanliness of a given heating surface is calculated using available measurements of process parameters based on the epsilon-NTU method. The calculations are carried out in the DCS system for each surface individually (air and water heaters, evaporator, superheaters). During the standard operation of the boiler, the adopted methodology was verified, having analysed the usefulness of the tool to assess the boiler cleanliness under operating condition.

Large coal-fired power plants were typically designed as a base load units. Any changes in load level, as well as start-up time, are noticeably slow on that kind of units. However, in order to adapt to changing market conditions with increasing number of renewable energy sources, coal-fired power plants need to improve their flexibility. In the paper, 200 MWe class unit has been taken into consideration. During the test campaign, a minimum safe load of the unit was decreased from 60 to 40%. Paper presents results of a model that was made using Ebsilon ® Professional software. The simulation model is comprised of boiler and turbine part of the power unit. Obtained results were validated using measurements collected from the test campaign. Parameters important from the technical and economical point of view were investigated. Results revealed that simulation model can be utilised successfully to scrutinise coal-fired units under off-design operation conditions. As the outcome of the performed analysis, a number of issues related to low load operation of the coal-fired unit are presented and discussed. Paper indicates sensitive areas that need to be addressed when operation in decreased safe load is considered. Finally, overall potential for flexibility improvement for 200 MWe class coal-fired units has been evaluated.

The paper presents a developed methodology of short-term forecasting for heat production in combined heat and power (CHP) plants using a big data-driven model. An accurate prediction of an hourly heat load in the day-ahead horizon allows a better planning and optimization of energy and heat production by cogeneration units. The method of training and testing the predictive model with the use of generalized additive model (GAM) was developed and presented. The weather data as an input variables of the model were discussed to show the impact of weather conditions on the quality of predicted heat load. The new approach focuses on an application of the moving window with the learning data set from the last several days in order to adaptively train the model. The influence of the training window size on the accuracy of forecasts was evaluated. Different versions of the model, depending on the set of input variables and GAM parameters were compared. The results presented in the paper were obtained using a data coming from the real district heating system of a European city. The accuracy of the methods during the different periods of heating season was performed by comparing heat demand forecasts with actual values, coming from a measuring system located in the case study CHP plant. As a result, a model with an averaged percentage error for the analyzed period (November–March) of less than 7% was obtained.

No abstract