For the prediction of heating energy consumption of university campus, neural network ensemble is proposed. Actual measured data are used for training and testing the models. Improvement of the prediction accuracy using k-means clustering for creating subsets used to train individual radial basis function neural networks is examined. Number of clusters is varying from 2 to 5. The outputs of ensemble members are aggregated using simple, weighted and median based averaging. It is shown that ensembles achieve better prediction results than the individual network.

Prediction of a building energy use for heating is very important for adequate energy planning. In this paper the daily district heating use of one university campus was predicted using the support vector machine model. Support vector machine is the artificial intelligence method that has recently proved that it can achieve comparable, or even better prediction results than the much more used artificial neural networks. The proposed model was trained and tested on the real, measured data. The model accuracy was compared with the results of the previously published models (various neural networks and their ensembles) on the same database. The results showed that the support vector machine model can achieve better results than the individual neural networks, but also better than the conventional and multistage ensembles. It is expected that this theoretically well-known methodology finds wider application, especially in prediction tasks.

Feedforward neural network models are created for prediction of heating energy consumption of a university campus. Actual measured data are used for training and testing the models. Multistage neural network ensemble is proposed for the possible improvement of prediction accuracy. Previously trained feed-forward neural networks are first separated into clusters, using k-means algorithm, and then the best network of each cluster is chosen as a member of the ensemble. Three different averaging methods (simple, weighted and median) for obtaining ensemble output are applied. Besides this conventional approach, single radial basis neural network in the second level is used to aggregate the selected ensemble members. It is shown that heating energy consumption can be predicted with better accuracy by using ensemble of neural networks than using the best trained single neural network, while the best results are achieved with multistage ensemble.

This paper presents the proportional-derivative fuzzy controller for trajectory tracking of the gripping mechanism with two degrees of freedom. Aiming to achieve movement of the gripping mechanism without sudden starting and stopping, a polynomial velocity profile is utilized. The African vultures optimization, as one of the latest metaheuristic algorithms, is used to obtain the optimal input/output scaling gains of the proposed fuzzy controller according to the selected fitness function. The results obtained by this algorithm are compared with the other three new and popular metaheuristic algorithms: the whale optimization, the ant lion optimization and the sine cosine algorithm. Moreover, a simulation study was done for the defined initial position and for the scenario where there is a certain deviation because the gripping mechanism is not at its original initial position. Finally, the robustness of the controller is tested for the case when the masses of the segments increase three times. The results revealed that the suggested controller was capable of dealing with nonlinearities of the gripping mechanism, initial position and parameter changes. The movement of the gripping mechanism is smooth and follows the defined trajectory.

The determination of the energy characteristics of a double-regulated hydro turbine is based on numerous measuring points during extensive and expensive experimental model tests in the laboratory and on site prototype tests at the hydropower plant. By the spatial interpolation of representative measured points that belong to the so-called on-cam curves for different speed factors, the hill performance diagram is obtained. The focus of the paper is the contemporary method of artificial neural network models use for the prediction of turbine characteristics, especially in not measured operation modes. A part of the existing set of experimental data for the Kaplan turbine energy parameters is used to train three developed neural network models. The reliability of applied method is considered by analysing, testing and validating the predicted turbine energy parameters in comparison with the remaining data.