Optimal and suboptimal minimum-variance filtering in networked systems with mixed uncertainties of random sensor delays,packet dropouts and missing measurements

In this paper the Kalman filtering problem for networked stochastic linear discrete-time systems with random measurement delays, packet dropouts and missing measurements is studied. Based on a quasi Markov-chain approach, a unified/combined model is developed to accommodate random delay, packet dropout and missing measurement. Two approaches for constructing a filter via the linear matrix inequality approach are proposed. Simulation studies are then conducted to evaluate the effectiveness of the constructed estimators.     

Proposing two new metaheuristic algorithms of ALO-MLP and SHO-MLP in predicting bearing capacity of circular footing located on horizontal multilayer soil

In this study, for the issue of shallow circular footing’s bearing capacity (also shown as F_ult), we used the merits of artificial neural network (ANN), while optimized it by two metaheuristic algorithms (i.e., ant lion optimization (ALO) and the spotted hyena optimizer (SHO)). Several studies demonstrated that ANNs have significant results in terms of predicting the soil’s bearing capacity. Nevertheless, most models of ANN learning consist of different disadvantages. Accordantly, we focused on the application of two hybrid models of ALO–MLP and SHO–MLP for predicting the F_ult placed in layered soils. Moreover, we performed an Extensive Finite Element (FE) modeling on 16 sets of soil layer (soft soil placed onto stronger soil and vice versa) considering a database that consists of 703 testing and 2810 training datasets for preparing the training and testing datasets. The independent variables in terms of ALO and SHO algorithms have been optimized by taking into account a trial and error process. The input data layers consisted of (i) upper layer foundation/thickness width (h/B) ratio, (ii) bottom and topsoil layer properties (for example, six of the most important properties of soil), (iii) vertical settlement (s), (iv) footing width (B), where the main target was taken F_ult. According to RMSE and R², values of (0.996 and 0.034) and (0.994 and 0.044) are obtained for training dataset and values of (0.994 and 0.040) and (0.991 and 0.050) are found for the testing dataset of proposed SHO–MLP and ALO–MLP best-fit prediction network structures, respectively. This proves higher reliability of the proposed hybrid model of SHO–MLP in approximating shallow circular footing bearing capacity.

     

K-Fold and State-of-the-Art Metaheuristic Machine Learning Approaches for Groundwater Potential Modelling

Groundwater being an essential resource is not easily available in some parts of the world. The present study, aimed at procuring better prediction maps for groundwater potential zones, is based on a novel approach combining the use of k-fold cross-validation method and the implementation of four scenarios, each comprising of six machine learning models, ANFIS (Adaptive Neuro Fuzzy Inference System) and five other ensembles of it, ANFIS-Firefly, ANFIS-Bees, ANFIS-GA, ANFIS-DE and ANFIS-ACO. Ada Boost Model has played a vital role in determining the collinearity among the fourteen conditioning factors, which are, Lithology, Slope, TST, TRI, LULC, HAND, Curvature, Distance to Stream, Distance to Fault, Rainfall, Fault Density, Drainage Density, Elevation and Aspect. The AUCROC (Area Under Curve – Receiver Operating Characteristics) approach was employed as a model evaluation metric along with Accuracy, Sensitivity and Specificity. Among the models, ANFIS-DE showed the most promising results, acquiring the highest average values among the four scenarios for AUC (0.934), Accuracy (0.987), Sensitivity (0.985) and Specificity (0.985). Promising results of this study gives the necessary incentive for further applying this approach for groundwater zonation of other areas of the world as well as other areas of hydrogeological studies.

     

A novel artificial intelligence technique to predict compressive strength of recycled aggregate concrete using ICA-XGBoost model

Engineering with Computers - Recycled aggregate concrete is used as an alternative material in construction engineering, aiming to environmental protection and sustainable development. However, the...     

Optimizing ANN models with PSO for predicting short building seismic response

The present study aimed to optimize the artificial neural network (ANN) with one of the well-established optimization algorithms called particle swarm optimization (PSO) for the problem of ground...     

An artificial neural network approach for under-reamed piles subjected to uplift forces in dry sand

The present study is about under-reamed pile subjected to uplift forces. They are known to be very effective especially against uplift forces. The objective is to develop a simple design formula based on an optimized artificial neural network (ANN) predictive approach model. This formula can calculate the ultimate uplift capacity of under-reamed piles (P_ul) embedded in dry cohesionless soil with excellent accuracy. The new generated ANN model was developed by taking into account the key factors such as under-reamed base diameter, angle of enlarged base to the vertical axis, shaft diameter, and embedment ratio. The proposed approach shows excellent agreement with a mean absolute error (MAE) less than 0.262, which is better than previous theories.

     

Swarm-based analysis through social behavior of grey wolf optimization and genetic programming to predict friction capacity of driven piles

Engineering with Computers - The advantage of new data mining-based solutions, and more recently, optimization algorithms (i.e., basically swarm-based solutions) have enhanced traditional...     

Sine cosine grey wolf optimizer to solve engineering design problems

Balancing the exploration and exploitation in any nature-inspired optimization algorithm is an essential task, while solving the real-world global optimization problems. Therefore, the search agents of an algorithm always try to explore the unvisited domains of a search space in a balanced manner. The sine cosine algorithm (SCA) is a recent addition to the field of metaheuristics that finds the solution of an optimization problem using the behavior of sine and cosine functions. However, in some cases, the SCA skips the true solutions and trapped at sub-optimal solutions. These problems lead to the premature convergence, which is harmful in determining the global optima. Therefore, in order to alleviate the above-mentioned issues, the present study aims to establish a comparatively better synergy between exploration and exploitation in the SCA. In this direction, firstly, the exploration ability of the SCA is improved by integrating the social and cognitive component, and secondly, the balance between exploration and exploitation is maintained through the grey wolf optimizer (GWO). The proposed algorithm is named as SC-GWO. For the performance evaluation, a well-known set of benchmark problems and engineering test problems are taken. The dimension of benchmark test problems is varied from 30 to 100 to observe the robustness of the SC-GWO on scalability of problems. In the paper, the SC-GWO is also used to determine the optimal setting for overcurrent relays. The analysis of obtained numerical results and its comparison with other metaheuristic algorithms demonstrate the superior ability of the proposed SC-GWO.

     

Networked LQG control over lossy channels with computational/packet-transmission delays and coarsely quantised packets

This article addresses the linear quadratic Gaussian (LQG) control problem of networked multi-input, multi-output systems where computational delay exists and the measurement and control signals are packetised and transmitted through a network within which random delay and packet loss may occur during transmissions. A transmission control protocol (TCP)-like protocol for the communication network is considered in which acknowledgement is sent from the actuator to the controller if and only if the control packet is received, assuming these acknowledgements always reach the estimator in time and without fail. To minimise the data word-length for transmissions over the network and to maximise control system performance, it is proposed that different quantisation resolutions be used for transmission data encapsulation, and control and output signals A/D-D/A conversions at sensor/actuator. To circumvent the problem of disparity between encapsulation and A/D-D/A quantisation resolutions, a pseudo-stochastic approach via subtractive dither is applied to quantise the transmission packets. This also enables us to model the quantisation errors as uncorrelated independent zero-mean additive white noises and apply standard LQG methodology and separation principle to design the estimator and the controller separately. An example is included to demonstrate the effectiveness of the approach.