Implementing ANN to minimize sewage systems concrete corrosion with glass beads substitution

Abstract

Sewage system collapse is a widespread problem due to induced sulfuric acid corrosion by sulfur-oxidizing bacteria. Numerous studies tried to enhance concrete performance which led to contradictory results; this matter signifies on dissimilar laboratory conditions and results analysis methods. Glass is known as one of the most resistant materials against sulfuric acid (H2SO4) attack; it can be assumed that concretes containing glass powder have acidic resistance as well. The high silica content in both glass powder and microsilica clear the way for comparing their effects on the durability of self-consolidating and ordinary concretes with the same packing density in the H2SO4 medium. Different concrete relationships were elicited among concrete characteristics by performing statistical analyses. Artificial neural networks (ANN) was employed to predict the mass-loss and volume-loss in the specimens. It was found that both the substitutional materials used were capable of enhancing sewer durability.