Search

Ecological concrete has excellent water and air permeability, which not only is conducive to plant growth but also allows surface water to infiltrate underground and intercept pollutants. The performance of ecological concrete is largely determined by the nature of the raw materials and their relative content. Therefore, mastering the optimal design method for the mix proportion of ecological concrete is crucial to achieving good performance. In the current research, there is a lack of systematic intelligent decision-making models for predicting performance and optimizing mix proportions. In this paper, four factors, namely mechanical properties, water permeability, decontamination properties, and planting properties of ecological concrete, were considered when evaluating the comprehensive performance of ecological concrete. The evaluation was conducted using the analytic hierarchy process (AHP). The gray wolf optimizer (GWO) was introduced to enhance the backpropagation (BP) neural network, and an optimization model for finding the optimal ecological concrete mix proportion was established. The optimal mix proportion of two types of typical ecological concrete, one for filtration and one for plant growth, was discussed. The results indicate that the AHP-GWO-BP model calculates the optimal mixing proportion of filtration ecological concrete as follows: The diameter of coarse aggregate is 10–15 mm, with adsorbed coarse aggregate accounting for 49.7%, a component ratio is 118%, the water–cement ratio should be 28.7%, and the silica fume mix ratio should be 32.1%. According to the given parameters, the performance test of ecological concrete is conducted, with a coarse aggregate size of 12 mm. The results showed that under these parameters, the compressive strength was 12.3 MPa, the flexural strength was 3.35 MPa, the water permeability coefficient was 14.87 cm s−1, the porosity was 27.23%, the removal rate of total nitrogen was 80.56%, the removal rate of total phosphorus was 67.33%, the pH was 9.16, and the plant dry weight was 9.37 g. The optimal mix proportion of the planting ecological concrete is as follows: The diameter of the coarse aggregate is 20–25 mm, the adsorbed coarse aggregate accounts for 49.7%, its component ratio is 138%, the water–cement ratio should be 27.3%, and the silica fume mix ratio should be 34.1%.Highlights: An orthogonal test optimization method based on AHP-GWO-BP neural network Two types of multi-aggregate ecological concrete utilizing multiple adsorbent materials as coarse aggregates Simulation and prediction of various aspects of the performance of ecological concrete under different factors [ABSTRACT FROM AUTHOR]

AI approaches have been introduced to predict the remaining useful life (RUL) of a machine in modern industrial areas. To apply them well, challenges regarding the high dimension of the data space and noisy data should be met to improve model efficiency and accuracy. In this study, we propose an end-toend model, termed ACB, for RUL predictions; it combines an autoencoder, convolutional neural network (CNN), and bidirectional long short-term memory. A new penalized root mean square error loss function is included to avoid an overestimation of the RUL. With the CNN-based autoencoder, a high-dimensional data space can be mapped into a lower-dimensional latent space, and the noisy data can be greatly reduced. We compared ACB with five state-of-the-art models on the Commercial Modular Aero-Propulsion System Simulation dataset. Our model achieved the lowest score value on all four sub-datasets. The robustness of our model to noise is also supported by the experiments. [ABSTRACT FROM AUTHOR]