INTELLIGENT APPROACHES TO ORGANIZING REMOTE QUALITY CONTROL OF STORAGE OF GRAIN PRODUCTS

Cereals are an essential part of the diet of Homo sapiens. Since late Neolithic times, with the transition to sedentary farming, working with grain (growing, storing, processing, cooking food) has become a traditional type of professional human activity. As part of the accumulated historical experience, numerous technological processes have been developed and optimized for this type of activity. The relevant technologies evolved in close correlation with the changing conditions of life, literally under the pressure of Darwinian natural selection, because they were directly related to the survival of the Homo sapiens. Further development of grain-processing technologies remains invariably urgent today, as evidenced by the report [1] presented by the UN on the state of food security and nutrition in the world - with horrifying figures depicting the need and misery of the wide masses of the population of the planet. An important component of grain processing is the technology associated with the storage of grain products. Part of the stored grain products is used as seed stock for a new cycle of grain sales, the other - a significant part - for processing into food products. At the same time, new developed (optimized, improved) grain storage technologies must be safe, low-cost, maximally compatible with previously developed (available) equipment, and scalable to large volumes of stored material. Of course, the technology must ensure proper efficiency, an indicator of which should be a reduction in the percentage of grain product losses. In this regard, management methods used in the technological processes of grain products storage are substantially important, as well as methods of control over the current state of grain products for the correct organization of the technological processes. In particular, methods using elements of artificial intelligence are of high interest. Among them, neural networks are promising, especially those capable of learning "without a teacher" - Kohonen Maps (KK). Modified KK algorithm [2] implements reduced learning time[3], which is relevant in the implementation of adaptive procedures for processing the results of measurements of controlled parameters. The purpose of this paper is to consider the principles of using modified Kohonen maps to classify situations with applicability to remote quality control of grain products storage.

The experimental study of the effectiveness of Kohonen maps and autoassociative neural networks in the qualitative analysis of multidimensional data by the example of real data describing coal susceptibility to fluidal gasification

The qualitative analysis of multidimensional data using their visualization allows to observe some characteristics of data in a way which is the most natural for a human, through the sense of sight. Thanks to such an approach, some characteristics of the analyzed data are simply visible. This allows to avoid using often complex algorithms allowing to examine specific data properties. Visualization of multidimensional data consists in using the representation transforming a multidimensional space into a two-dimensional space representing a computer screen. The important information which can be obtained in this way is the possibility to separate points belonging to different classes in the multidimensional space. Such information can be directly obtained if images of points belonging to different classes occupy other areas of the picture presenting these data. The paper presents the effectiveness of the qualitative analysis of multidimensional data conducted in this way through their visualization with the application of Kohonen maps and autoassociative neural networks. The obtained results were compared with results obtained using the perspective-based observational tunnels method, PCA, multidimensional scaling and relevance maps. Effectiveness tests of the above methods were performed using real seven-dimensional data describing coal samples in terms of their susceptibility to fluidal gasification. The methods’ effectiveness was compared using the criterion for the readability of the multidimensional visualization results, introduced in earlier papers.