Predicting stress-strain behavior of normal weight and lightweight aggregate concrete exposed to high temperature using LSTM recurrent neural network

Lightweight aggregate is commonly used to reduce the self-weight of concrete elements which can efficiently mitigate environmental impact. This study investigates mechanical performance normal weight (NWAC) and (LWAC) exposed high temperature, focusing on developing a predictive model for stress-strain relationship LWAC based property cement, silica fume, light water/cement ratio. Mechanical properties 30 different mixtures, including uniaxial compressive stress–strain relationship, strength, modulus elasticity, failure strain are determined before after temperature exposures at 250, 500, 750 °C. Results show that elasticity strength increased with exposure temperature. In particular, mixture S4 was found outperform other retained 96, 75, 46 % following °C, respectively. At all temperatures investigated, specimens this were able achieve satisfactory maximum strain. The prepared mixtures containing 75 LECA (S23) showed higher retention also utilizes long short-term memory (LSTM) neural network predict NWAC temperatures. results LSTM could adequately both in terms elevated