The aim of this paper is a comparative analysis of the experimental test results of twenty T-section beams reinforced with glass fiber reinforced polymer (GFRP) bars without stirrups with predicted values of the shear capacity according to the following design guidelines: draft Eurocode 2, Japanese JSCE, American ACI 440, Italian CNR- DT-203/2006, British BS according to fib Bulletin 40, Canadian CSA-S806-12 and ISIS-M03-07. Standard procedures for FRP reinforced beams based on traditional steel reinforced concrete guidelines. The longitudinal FRP reinforcement has been taken into account by its stiffness reduction related to the steel reinforcement. A basis of this modification is the assumption that the FRP-to-concrete bond behaviour is the same as it is for steel reinforcement. To assess the compatibility of predicted values (Vcal) with the experimental shear forces (Vtest) the safety coefficient η = Vtest / Vcal was used. The results corresponding to values η < 1 indicates overestimation of the shear capacity, but η > 1 means that shear load capacity is underestimated. The most conservative results of the calculated shear capacity are obtained from the ACI 440 standard. In contrast to them the best compatibility of the calculated shear values to the experimental ones indicated British BS standard, fib Bulletin 40 and Canadian CSA-S806-12 standard.

The current machine vision-based surface roughness measurement mainly relies on the design of feature indicators associated with roughness to measure the surface roughness. However, the process is tedious and complicated. Moreover, most existing deep learning methods for workpiece surface roughness measurement use a monochromatic light source to acquire images. In the case of surface roughness in a grinding process with low roughness and random texture characteristics, the feature information obtained by monochromatic light source acquisition is relatively small. It is difficult to extract the workpiece surface roughness features, which can easily cause problems for subsequent measurement. Based on the problems above, this paper proposes a grinding surface roughness measurement method combining red-green information and a convolutional neural network. The technique uses a particular red-green block to highlight the grinding surface texture features. Finally, it classifies the grinding surface roughness measurement with a classification detection technique of the convolutional neural network. Experimental results show that the accuracy of the grinding surface roughness measurement method combining red-green information and the convolutional neural network is significantly improved compared with that of the grinding surface roughness measurement method without using the red-green data.