The paper presents the operation of two neuro-fuzzy systems of an adaptive type, intended for solving problems of the approximation of multi-variable functions in the domain of real numbers. Neuro-fuzzy systems being a combination of the methodology of artiﬁcial neural networks and fuzzy sets operate on the basis of a set of fuzzy rules “if-then”, generated by means of the self-organization of data grouping and the estimation of relations between fuzzy experiment results. The article includes a description of neuro-fuzzy systems by Takaga-Sugeno-Kang (TSK) and Wang-Mendel (WM), and in order to complement the problem in question, a hierarchical structural self-organizing method of teaching a fuzzy network. A multi-layer structure of the systems is a structure analogous to the structure of “classic” neural networks. In its ﬁnal part the article presents selected areas of application of neuro-fuzzy systems in the ﬁeld of geodesy and surveying engineering. Numerical examples showing how the systems work concerned: the approximation of functions of several variables to be used as algorithms in the Geographic Information Systems (the approximation of a terrain model), the transformation of coordinates, and the prediction of a time series. The accuracy characteristics of the results obtained have been taken into consideration.
Open pit mining of rock minerals and the affected areas requiring further development are a serious challenge for shaping the positive image of the mining industry among the public. The direction and method of post-mining land reclamation are important for this image, which should take into account various factors describing the mining area, including social preferences. The article presents an example solution – fuzzy system (FSDR) – which supports the selection of the direction of reclamation of post-mining areas created after the termination of operations of open pit gravel and sand natural aggregate mines. The article presents selected factors determining the selection of the direction and possible reclamation variants as input and output data of the fuzzy system. The rules base of the developed system, as well as the mechanisms of inference and defuzzification, were also characterized. The application of the developed system is presented on selected examples.
The quality of the squeeze castings is significantly affected by secondary dendrite arm spacing, which is influenced by squeeze cast input parameters. The relationships of secondary dendrite arm spacing with the input parameters, namely time delay, pressure duration, squeeze pressure, pouring and die temperatures are complex in nature. The present research work focuses on the development of input-output relationships using fuzzy logic approach. In fuzzy logic approach, squeeze cast process variables are expressed as a function of input parameters and secondary dendrite arm spacing is expressed as an output parameter. It is important to note that two fuzzy logic based approaches have been developed for the said problem. The first approach deals with the manually constructed mamdani based fuzzy system and the second approach deals with automatic evolution of the Takagi and Sugeno’s fuzzy system. It is important to note that the performance of the developed models is tested for both linear and non-linear type membership functions. In addition the developed models were compared with the ten test cases which are different from those of training data. The developed fuzzy systems eliminates the need of a number of trials in selection of most influential squeeze cast process parameters. This will reduce time and cost of trial experimentations. The results showed that, all the developed models can be effectively used for making prediction. Further, the present research work will help foundrymen to select parameters in squeeze casting to obtain the desired quality casting without much of time and resource consuming.
The paper presents Gupta's relational decomposition technique expanded on linguistic level. It allows to reduce the hardware cost of the fuzzy system or the computing time of the final result, especially when referring to First Aggregation Then Inference (FATI) relational systems or First Inference Then Aggregation (FITA) rule systems. The inference result of the hierarchical system using decomposition technique is more fuzzy than of the classical system. The paper describes a linguistic decomposition technique based on partitioning the knowledge base of the fuzzy inference system. It allows to decrease or even totally remove a redundant fuzziness of the inference result.
The operational mineral deposit reconnaissance tends to evaluate its parameters to conduct safe and profitable production. Particular deposit parameters, important from the point of mineral deposit management, are estimated on the basis of observations carried out by mining geological surveys. These observations usually involve sampling, drilling, laboratory analyses and others. The use of fuzzy description to assess the parameters of the mineral deposit was proposed in the paper. In the fuzzy characteristics, an imprecise descriptive description appeared in place of a particular numerical quantity. This approach was used to description of the ore deposit features (metal content, volume, and metal yield) by assigning them specific characteristic functions, whose distributions were based on basic statistical quantities. Characteristic functions can be used to prepare operational strategies for any configuration of required deposit parameters resulting from the production management needs. For this purpose, selected logical operators of fuzzy sets were used. In the next approach to fuzzy modeling, an opportunity to characterize the deposit in a subjective approach was indicated, where the assessment of the deposit parameters is based on rough, in some way, discretionary observation and evaluation. Such model construction enabled the overall assessment of the deposit from the point of view of any parameters. Through the implementation of appropriate inference rules, adequate fuzzy control planes were obtained, which may also be useful in the context of operational mine strategy planning.
A solar photovoltaic (PV) system has been emerging out as one of the greatest potential renewable energy sources and is contributing significantly in the energy sector. The PV system depends upon the solar irradiation and any changes in the incoming solar irradiation will affect badly on the output of the PV system. The solar irradiation is location specific and also the atmospheric conditions in the surroundings of the PV system contribute significantly to its performance. This paper presents the cumulative assessment of the four MPPT techniques during the partial shading conditions (PSCs) for different configurations of the PV array. The partial shading configurations like series-parallel, bridge link, total cross tied and honeycomb structure for an 8#2;4 PV array has been simulated to compare the maximum power point tracking (MPPT) techniques. The MPPT techniques like perturb and observe, incremental conductance, extremum seeking control and a fuzzy logic controller were implemented for different shading patterns. The results related to the maximum power tracked, tracking efficiency of each of the MPPT techniques were presented in order to assess the best MPPT technique and the best configuration of the PV array for yielding the maximum power during the PSCs.
Abstract. In this paper we present a new class of neuro-fuzzy systems designed for system modelling and pattern classi.cation. Our approach is characterized by automatic determination of fuzzy inference in the process of learning. Moreover, we introduce several .exibility concepts in the design of neuro-fuzzy systems. The method presented in the paper is characterized by high accuracy which outperforms previous techniques applied for system modelling and pattern classi.cation.