The utilization of waste material, such as fly ash, in the concrete industry will provide a valuable alternative solution for creating an eco-friendly environment. However, experimental work is time-consuming; employing soft machine learning techniques can accelerate the process of forecasting the strength properties of concrete. Ensemble machine learning modeling using Python Jupyter Notebook was employed in the forecasting of compressive strength (CS) of high-performance concrete. Multilayer perceptron neuron network (MLPNN) and decision tree (DT) were used as individual learning which then ensembled with bagging and boosting to provide strong correlations. Random forest (RF) and gradient boosting regression (GBR) were also used for prediction. A total of 471 data points with input parameters (e.g., cement, fine aggregate, coarse aggregate, superplasticizer, water, days, and fly ash), and an output parameter of compressive strength (CS), were retrieved to train and test the individual learners. Cross-validation with K-fold and statistical error (i.e., MAE, MSE, RMSE, and RMSLE) analysis was applied to check the accuracy of all models. All models showed the best correlation with an ensemble model rather than an individual one. DT with AdaBoost and random forest gave a strong correlation of R2 = 0.89 with fewer errors. Cross-validation results revealed a good response with an error of less than 10 MPa. Thus, ensemble modeling not only trains the data by employing several weak learners but also produces a robust correlation that can then be used to model and predict the mechanical performance of concrete.

Historic interiors with large cubature, such as reception, theatrical, and concert halls, need to be renovated periodically if they are to be preserved as cultural heritage for future generations. In such cases it is necessary to maintain appropriate balance between requirements imposed by heritage conservation authorities office which are usually being given a higher priority, applicable safety regulations, and the comfort of use, including good acoustics.The paper is a presentation of architectural interference in three historic interiors with large cubature leading to changes in their acoustic qualities. In two cases, the changes were beneficial to the functional qualities of the halls to satisfaction of the investors carrying out the renovation work. In the third instance, the architectural interference aimed at showing off the monumental valor of the interior resulted in significant degradation of its acoustics. To remedy the situation impairing the functional program of the facility, corrective measures are proposed neutral with respect to its historic character.

This paper proposes the use of X-ray computed tomography (µCT, xCT) measurements together with finite element method (FEM) numerical modelling to assess bond failures mechanism of fiber-reinforced fine-grain concrete. Fiber-reinforced concrete is becoming popular for application in civil engineering structures. A dynamically developing topic related to concretes is the determination of bond characteristics. Nowadays, modern technologies allow inspecting the inside of the element without the need to damage its structure. This paper discusses the application of computed tomography in order to identify damage occurring in the structure of fiber-reinforced fine-grain concrete during bond failure tests. The publication is part of a larger study to determine the bonding properties of Ukrainian steel fibers in fine-grain concrete. The authors focused on the visual evaluation of sections obtained from tomographic data. Separately, the results of volumetric analysis were presented to quantitatively assess the changes occurring in the matrix structure. Finite element analysis is an addition to the substantive part and allows us to compare real damage areas with theoretical stress concentration areas. The result of the work is the identification of a path that allows verification of the locations where matrix destruction occurs.

The results of tests for drawing anchor fibers with a length of 50 mm and a diameter of 1 mm, laid at the end of concrete prisms 50x50x100 mm made of fine-grained concrete of classes C 20/25, C25/30 and C 30/35 are presented. From the tests of 50 fibers, the average value of tensile strength was determined, which is equal to 1242 MPa with a coefficient of variation of 2.1%. Prisms were made of fine-grained concrete, which included cement with an activity of 41.2 MPa for concrete class C 20/25 and an activity of 50.8 MPa for concrete classes C 25/30 and C 30/35. Sand with a modulus of size 2.1 was used as a filler. The concrete mixture was prepared in a forced concrete mixer, and the concrete was compacted on a vibrating platform. Simultaneously with these prisms, cubes with dimensions of 150x150x150 mm and prisms with dimensions of 100x100x400 mm were made to determine the bottom and prism strength of concrete. The length of laying fibers into concrete was 10,15 and 25 mm. It is shown that the forces perceived by the end anchors and the smooth part of the fibers rise with increasing strength of concrete. The results of tests for drawing fibers from concrete prisms are given in tables 1 - 3. For the length of laying fiber 10 mm into prisms with strength fcm,cube = 29.31MPa and fcm,prism = 23.15MPa the maximum stresses during drawing were 515.30 - 549.04 MPa (average value - 532.10 MPa). At the same length of laying fiber into concrete prisms with strength fcm,cube = 34.76MPa and fcm,prism = 27.11MPa, these stresses were equal to 554.47 - 588.54 MPa (average value - 569.70 MPa). For the length of laying the fiber 10 mm into prisms with strength fcm,cube = 38.96MPa and fcm,prism = 31.14MPa, the maximum tensile stresses were 590.51 - 621.72 MPa (average value - 606.81MPa). At the specified strengths of the prism concrete, the maximum values of the average stresses for fiber drawing were on average 13.37 MPa for concrete of class C20/25, 14.34 MPa for concrete of class C25/30 and 15.27 MPa for concrete of class C30/35. With a fiber laying length of 15 mm into prisms with concrete strength corresponding to class C20/25, the maximum tensile stresses were 575.80 - 607.64 MPa (average value - 587.10 MPa). With such a length of laying fiber into prisms made of concrete class C25/30, these stresses were equal to 614.44 - 680.25 MPa (average value - 638.95 MPa). At the length of laying the fiber 15 mm into the prisms of concrete class C30/35, the maximum stresses during drawing were 681.14 - 692.99 MPa (average value - 685.44 MPa). The maximum values of average stresses for fiber drawing were on average 9.87 MPa for concrete of class C20/25, 10.70 MPa for concrete of class C25/30 and 11.52 MPa for concrete of class C30/35. At a fiber laying length of 25 mm into prisms with concrete strength corresponding to class C20/25, the maximum tensile stresses were 645.44 - 735.03 MPa (average value - 692.76 MPa). With such a length of laying fiber into prisms made of concrete class C25/30, these stresses were equal to 736.58 - 773.25 MPa (average value - 752.37 MPa). With the length of laying fiber 25 mm into prisms made of concrete class C30/35, maximum stresses during drawing were equal to 780.27 - 839.49 MPa (average value - 809.12 MPa). The maximum values of the average stresses during fiber drawing were on average 6.97 MPa for concrete of class C20/25, 7.57 MPa for concrete of class C25/30 and 8.12 MPa for concrete of class C30/35. The coefficient of anchoring capacity η, which under Ukrainian standards of fibroconcrete structures designing is equal to 0.9, as shown by the data of our experiments, is not constant, so it is necessary to take this into account in the formula for determining the tensile strength of fibroconcrete.