Prediction of Geopolymer Concrete Compressive Strength Using Convolutional Neural Networks

Geopolymer concrete emerges as a promising avenue for sustainable development and offers an effective solution to environmental problems.Its attributes as a non-toxic,low-carbon,and economical substitute for conventional cement concrete,coupled with its elevated compressive strength and reduced shrinkage properties,position it as a pivotal material for diverse applications spanning from architectural structures to transportation infrastructure.In this context,this study sets out the task of using machine learning(ML)algorithms to increase the accuracy and interpretability of predicting the compressive strength of geopolymer concrete in the civil engineering field.To achieve this goal,a new approach using convolutional neural networks(CNNs)has been adopted.This study focuses on creating a comprehensive dataset consisting of compositional and strength parameters of 162 geopolymer concrete mixes,all containing Class F fly ash.The selection of optimal input parameters is guided by two distinct criteria.The first criterion leverages insights garnered from previous research on the influence of individual features on compressive strength.The second criterion scrutinizes the impact of these features within the model’s predictive framework.Key to enhancing the CNN model’s performance is the meticulous determination of the optimal hyperparameters.Through a systematic trial-and-error process,the study ascertains the ideal number of epochs for data division and the optimal value of k for k-fold cross-validation—a technique vital to the model’s robustness.The model’s predictive prowess is rigorously assessed via a suite of performance metrics and comprehensive score analyses.Furthermore,the model’s adaptability is gauged by integrating a secondary dataset into its predictive framework,facilitating a comparative evaluation against conventional prediction methods.To unravel the intricacies of the CNN model’s learning trajectory,a loss plot is deployed to elucidate its learning rate.The study culminates in compelling findings that underscore the CNN model’s accurate prediction of geopolymer concrete compressive strength.To maximize the dataset’s potential,the application of bivariate plots unveils nuanced trends and interactions among variables,fortifying the consistency with earlier research.Evidenced by promising prediction accuracy,the study’s outcomes hold significant promise in guiding the development of innovative geopolymer concrete formulations,thereby reinforcing its role as an eco-conscious and robust construction material.The findings prove that the CNN model accurately estimated geopolymer concrete’s compressive strength.The results show that the prediction accuracy is promising and can be used for the development of new geopolymer concrete mixes.The outcomes not only underscore the significance of leveraging technology for sustainable construction practices but also pave the way for innovation and efficiency in the field of civil engineering.

F类火灾水系灭火剂灭火性能评价试验研究

为建立科学、统一的F类火灾水系灭火剂灭火性能评价试验方法,通过实验考察了油锅类型、灭火剂供给强度、喷头类型、食用油类型、用量等因素对灭火效果的影响,最终确定了适宜的试验方法,并对试验方法的有效性进行了验证。结果表明,该方法可有效区分不同F类火灾水系灭火剂产品之间的灭火性能差异,以及F类火灾水系灭火剂与水成膜泡沫灭火剂等其他灭火剂,并与现行厨房灭火装置标准协调一致。

F类火的灭火研究

通过对F类火燃烧特性的研究以及目前F类火的国内外灭火方法的分析,得出如下结论:F类火灭火难度超过B类火,我国应建立应对F类火的防范机制,尤其是国内用于家庭厨房的F类火灭火器急需填补空白。

Effects of Characteristics of Fly Ash on the Properties of Geopolymer

The properties of two types of fly ash geopolymers made from class F fly ashes produced in wet bottom and dry bottom boilers were investigated in the present study. The source material used in the geopolymer concrete was activated with sodium hydroxide and sodium silicate solution. The results revealed that the geopolymer produced with wet bottom boiler fly ash(CZ-FA)hardened quickly, and had higher early-age strength and lower shrinkage than the geopolymer produced with dry bottom boiler fly ash(SX-FA). The compressive strength of the two geopolymers made from CZ-FA and SX-FA was 45 MPa and 15 MPa respectively when cured at 60 ℃ and delayed for 14 d. However, after 90 days' delay, the compressive strength of both the samples is almost the same, up to 80 MPa. Nearly 20% volume shrinkage of the samples made from SX-FA was much higher than that made from CZ-FA, which was almost zero. XRD, SEM/EDS and FT-IR were used to analyze the main reason of the differences.

Bearing ratio and leachate analysis of pond ash stabilized with lime and lime sludge

Recycling of industrial waste is one of the effective ways to overcome their disposal problem. Ash produced by thermal power plants and lime sludge produced by paper mills require huge disposal land and may create environmental problems such as dusting and leaching of harmful heavy metals. Stabilization of the ash can improve its engineering properties and address the environmental problems. This paper reports the laboratory test results of a Class F pond ash stabilized with lime(2%, 4%, 6% and 8% by weight)alone and in combination with lime sludge(5%, 10% and 15% by weight). The X-ray diffraction(XRD) and scanning electron micrograph(SEM) tests were also performed to identify the possible formation of crystalline phases after stabilization. The effects of lime sludge on the unsoaked and soaked bearing ratios of pond ash with different lime contents, after 7 d, 28 d and 45 d of curing, were observed. Test results indicated that the bearing ratio increased considerably up to a 4% lime content which can be taken as the optimum lime content. Further increase in lime content increased bearing ratio gradually but at a slower rate. The effect of lime sludge was more pronounced at the optimum lime content,particularly at a low curing period. Lime sludge improved the bearing ratio in soaked condition significantly. Leachate analysis of stabilized ash was performed using toxicity characteristic leaching procedure(TCLP-1311) method. The concentrations of toxic elements Zn, Cu, Cd, Ni and Cr in the stabilized mixes were lower than those in the unstabilized waste. The results indicated that the pond ash-lime-lime sludge mixes have potential application as road subbase material.

Experiences of Using Alternative Raw Materials in Manufacturing of Refractory Materials

The article describes the experiences of alternative materials for the manufacturing of the refractory materi- als in the company P-D Refractories CZ a. s. The atten- tion is focused on energy by-products （EBP）. Energy by-products are generated during burning and desul- phurization in thermal power plants. Classical high-tem- perature -fly ash （class F.fly ash according to ASTM C618） is the most important and .fly ash from .fluidized technology （ class C-fly ash） is the second group. In the Czech Republic, power plants produce about 14 million tons of energy by-products every year. Utilization of these products in ceramic technology means a reduction of raw material costs and also it helps to reduce adverse environ- mental impact. Class F-fly ash （ FFA ） and cinder from high temperature combustion （CD） were used in light- weight insulation fireclay bricks. We can use these mate- rials as a grog and a lightening agent for materials with bulk density over 900 kg · m-3 and classification tem- perature up to 1 150 ℃. Class C.fly ash （CFA） is be- ing tested in a wide range of the refractory materials. For example, it can be used in lightweight fireclay bricks, fireclay bricks for stoves, acid-resistant fireclay bricks or refractory castables. The range of potential products, where EBP could be used, is very wide and energy by-products have become an important raw mate- rial source.