The estimation of the unit weight of soil is carried out using laboratory methods; however, it requires high-quality research material in the form of samples with undisturbed structures, the acquisition of which, especially in the case of organic soils, is extremely difficult, time-consuming and expensive. This paper presents a proposal to use artificial neural networks to estimate the unit weight of local organic soils as leading parameters in the process of checking the load capacity of subsoil, under a direct foundation in drained conditions, in accordance with current standards guidelines. The initial recognition of the subsoil, and the locating of organic soils at the Theological and Pastoral Institute in Rzeszow, was carried out using a mechanical cone penetration test (CPTM), using various interpretation criteria, and then, material for laboratory tests was obtained. The analysis of the usefulness of the artificial intelligence method, in this case, was based on data from laboratory tests. Standard multi-layer backpropagation networks were used to predict the soil unit weight based on two leading variables: the organic content LOIT and the natural water content w. The applied neural model provided reliable prediction results, comparable to the standard regression methods.

This paper draw attention to problems connected with recognize, classification, nomenclature and researches of organic soils according to Eurocode 7 and connected standards. Gather and put together current standard recommendation in the subject matter. Related to another guidelines and point on necessity to specify and supplement the recommendations.

Laboratory tests of strain properties on a selected peat from Rzeszow. Sampling methods for soil of undisturbed structure and methodology of oedometric tests. These tests were carried out under procedures set by Polish standards, using for this purpose a set of oedometers with an automatic system of data acquisition GEOLAB. The oedometric tests conducted on peat samples in a possibly wide range permitted, on the basis of obtained average values, to develop curves of: primary loading, unloading and reloading. These curves show strain properties of the tested soil under an applied load. The specific values of oedometric moduli of primary loading, unloading and reloading obtained from own tests were subjected to an elementary statistical analysis. Due to a potential heterogeneity of the tested peat, the values of coefficients of variation were also determined with regard to a specific range of vertical stresses. While analysing tests results, it was noticed that the deformation of peat, exposed to a load that causes the highest primary loading, makes up to 40% against the primary height of the sample. After an unloading process was carried out according to standard guidelines and after the reloading process with identical loads took place, it turned out that an average deformation caused by the highest secondary stress increase not exceed 3% of primary strains. A conclusion can be drawn that if there is a need for improvement of this type of soil for construction purposes, they must undergo consolidation.

No abstract

Abstract. The proposal of investigations of soft organic soils in a new calibration chamber performed at the Rzeszow University of Technology has been presented in this paper. The unique feature of this chamber is the possibility of simultaneous soil testing with the use of two penetrometers: FVT (Field Vane Test) and DPL (Dynamic Probing Light). It has been possible due to the large size of the cylindrical soil sample: 62.5 cm in diameter and max. 80 cm high. Additionally, a construction with a new calibration chamber has been described, concerning potential capabilities and restrictions when conducting researches. The presented calibration chamber ensures the stability of the parameters set during the tests, which allows one to compare the test results and search for the relationship between the analyzed parameters. Shear strength from the FVT test was adopted as reference. The results of preliminary research were presented and a detailed research plan was prepared, which will be implemented in the next stages of the investigations.