Detection of locally relevant variables using SOM–NG algorithm

The SOM–NG algorithm is a combination of the Self-Organizing Map and the Neural Gas algorithms. It was developed to combine quantization and topological preservation. The algorithm also has a supervised version to create local linear models of scalar fields in the defined Voronoi regions. In this work a new methodology is proposed to use those models as data mining tools. Using visual tools, gradients are analysed to discover the influence of each variable over the output. It does not only allow to select the most relevant variables but also to detect different zones of influence, which can be used to create a set of fuzzy rules. The proposed methodology is proven to be useful to detect locally relevant variables that lead to a better understanding of the data.     

Optimization of oval–round pass design using genetic algorithm

The primary purpose of this paper is to propose a computer aided optimal design system to support a generalized oval–round pass design, which is widely used as both intermediate and final passes in the process of rod rolling. This system, which is based on a hybrid model and the genetic algorithm, is developed to improve the efficiency, to reduce the manufacturing errors, as well as to extend the useful life of rolls through uniform wear design. Generalized parametric equations are established for geometrical modeling, graphic plotting of oval–round passes, as well as calculation of the cross section area, contact area and the lengths of contact arcs along the cross section of round groove in the MATLAB programming environment. Moreover, these equations can also realize the parametric transformation between roll profile and mathematical models for the oval–round pass design and optimization. The genetic algorithm is employed for the optimal design of oval–round passes in this paper. The objective functions are formulated for minimization of power consumption in the rolling process, variances between ideal dimensions and design dimensions, as well as variances between the lengths of contact arcs. To reduce the complexity and computational burden of the system, some reliable empirical formulas for the calculations of contact area and contact arc length are applied. Finally, the proposed approach is applied to an oval–round pass design. Through simulation and comparison of results against experimental data acquired from literature, it is found that this system is reliable, effective and easier to use.     

Numerical study and optimization of thermohydraulic characteristics of a graphene–platinum nanofluid in finned annulus using genetic algorithm combined with decision-making technique

Engineering with Computers - The heat transfer and flow attributes of a cylindrical microchannel heat sink (CMCHS) operated with a hybrid nanofluid containing the graphene nanoplatelets and...     

Analysis and design of single-phase power factor corrector with genetic algorithm and adaptive neuro-fuzzy-based sliding mode controller using DC–DC SEPIC

This paper proposes a methodology for single-phase power factor correction with DC–DC single-ended primary inductance converter (SEPIC) using cascade control strategy which comprises of genetic algorithm-based outer PI controller and an inner current controller which uses an adaptive neuro-fuzzy inference system-based sliding mode controller. DC–DC SEPIC is a fourth-order converter, and in order to reduce the complexity in controller design, reduced-order model of the original higher-order system is obtained by using Type-I Hankel matrix method. The performance of the proposed system is analysed using MATLAB/Simulink-based simulation studies. In order to ensure the robustness of the proposed controller, the performance parameters such as percentage total harmonic distortion, power factor, % voltage regulation, and % efficiency are analysed. From the simulation results, it is inferred that the proposed method provides efficient tracking of output voltage and effective source current shaping for load, line, and set point variations.

     

Application of genetic algorithm in crack detection of beam-like structures using a new cracked Euler–Bernoulli beam element

In this paper, a crack identification approach is presented for detecting crack depth and location in beam-like structures. For this purpose, a new beam element with a single transverse edge crack, in arbitrary position of beam element with any depth, is developed. The crack is not physically modeled within the element, but its effect on the local flexibility of the element is considered by the modification of the element stiffness as a function of crack's depth and position. The development is based on a simplified model, where each crack is substituted by a corresponding linear rotational spring, connecting two adjacent elastic parts. The localized spring may be represented based on linear fracture mechanics theory. The components of the stiffness matrix for the cracked element are derived using the conjugate beam concept and Betti's theorem, and finally represented in closed-form expressions. The proposed beam element is efficiently employed for solving forward problem (i.e., to gain accurate natural frequencies of beam-like structures knowing the cracks’ characteristics). To validate the proposed element, results obtained by new element are compared with two-dimensional (2D) finite element results as well as available experimental measurements. Moreover, by knowing the natural frequencies, an inverse problem is established in which the cracks location and depth are identified. In the inverse approach, an optimization problem based on the new beam element and genetic algorithms (GAs) is solved to search the solution. The proposed approach is verified through various examples on cracked beams with different damage scenarios. It is shown that the present algorithm is able to identify various crack configurations in a cracked beam.     

Automated fault detection in power distribution networks using a hybrid fuzzy–genetic algorithm approach

This paper describes the development of an intelligent technique based on artificial intelligence for automatically detecting incidents on power distribution networks. A hybrid combination of fuzzy logic and genetic algorithms (GAs) has been applied to detect faults in these networks. The robust nature of a fuzzy controller allows it to model functions of arbitrary complexity, while the maximising capabilities of GAs allow optimisation of the fuzzy design parameters to achieve optimal performance. The hybrid approach used in this paper builds on these individual strengths and seeks to blend fuzzy set and GAs techniques to compensate for their inadequacies. The technique for fault detection is described and verified with experiments on a 33 kV test system containing 12 busbars, eight transformers and eight line sections. The results obtained from the test data file of 500 test cases contain only one undetected case (0.2%), 458 correctly detected cases (91.6%) of actual faults and 41 cases (8.2%) where the protection system components either had not operated or had malfunctioned but were correctly identified by the incident detection system.     

Development of an epileptic seizure prediction algorithm using R–R intervals with self-attentive autoencoder

Epilepsy is a neurological disorder that may affect the autonomic nervous system (ANS) from 15 to 20 min before seizure onset, and disturbances of ANS affect R–R intervals (RRI) on an electrocardiogram (ECG). This study aims to develop a machine learning algorithm for predicting focal epileptic seizures by monitoring R–R interval (RRI) data in real time. The developed algorithm adopts a self-attentive autoencoder (SA-AE), which is a neural network for time-series data. The results of applying the developed seizure prediction algorithm to clinical data demonstrated that it functioned well in most patients; however, false positives (FPs) occurred in specific participants. In a future work, we will investigate the causes of FPs and optimize the developing seizure prediction algorithm to further improve performance using newly added clinical data.

     

Assessment of composite beam performance using GWO–ELM metaheuristic algorithm

Composite beams (CBs) include concrete slabs jointed to the steel parts by the shear connectors, which highly popular in modern structures such as high rise buildings and bridges. This study has investigated the structural behavior of simply supported CBs in which a concrete slab is jointed to a steel beam by headed stud shear connector. Determining the behavior of CB through empirical study except its costly process can also lead to inaccurate results. In this case, AI models as metaheuristic algorithms could be effectively used for solving difficult optimization problems, such as Genetic algorithm, Differential evolution, Firefly algorithm, Cuckoo search algorithm, etc. This research has used hybrid Extreme machine learning (ELM)–Grey wolf optimizer (GWO) to determine the general behavior of CB. Two models (ELM and GWO) and a hybrid algorithm (GWO–ELM) were developed and the results were compared through the regression parameters of determination coefficient (R²) and root mean square (RMSE). In testing phase, GWO with the RMSE value of 2.5057 and R² value of 1.2510, ELM with the RMSE value of 4.52 and R² value of 1.927, and GWO–ELM with the RMSE value of 0.9340 and R² value of 0.9504 have demonstrated that the hybrid of GWO–ELM could indicate better performance compared to solo ELM and GWO models. In this case, GWO–ELM could determine the general behavior of CB faster, more accurate and with the least error percentages, so the hybrid of GWO–ELM is more reliable model than ELM and GWO in this study.

     

Coupled particle swarm optimization method with genetic algorithm for the static–dynamic performance of the magneto-electro-elastic nanosystem

As a first attempt, Fourier series expansion (FSE), particle swarm optimization (PSO), and genetic algorithm (GA) methods are coupled for analysis of the static–dynamic performance and propagated waves in the magneto-electro-elastic (MEE) nanoplate. The FSE method is presented for solving the motion equations of the MEE nanoplate. For increasing the performance of genetic algorithms for solving the problem, the particle swarm optimization technique is added as an operator of the GA. Accuracy, convergence, and applicability of the proposed mixed approach are shown in the results section. Also, we prove that for obtaining the convergence results of the PSO and GA, we should consider more than 16 iterations. Finally, it is shown that if designers consider the presented algorithm in their model, the results of phase velocity of the nanosystem will be increased by 27%. A useful suggestion is that there is a region the same as a trapezium in which there are no effects from magnetic and electric potential of the MEE face sheet on the phase velocity of the smart nanoplate, and the region will be bigger by increasing the wavenumber.

     

Application of permutation genetic algorithm for sequential model building–model validation design of experiments

The work presented in this paper is motivated by a complex multivariate engineering problem associated with engine mapping experiments, which require efficient design of experiments (DoE) strategies to minimise expensive testing. The paper describes the development and evaluation of a Permutation Genetic Algorithm (PermGA) to enable an exploration-based sequential DoE strategy for complex real-life engineering problems. A known PermGA was implemented to generate uniform OLH DoEs, and substantially extended to support generation of model building–model validation (MB–MV) sequences, by generating optimal infill sets of test points as OLH DoEs that preserve good space-filling and projection properties for the merged MB + MV test plan. The algorithm was further extended to address issues with non-orthogonal design spaces, which is a common problem in engineering applications. The effectiveness of the PermGA algorithm for the MB–MV OLH DoE sequence was evaluated through a theoretical benchmark problem based on the Six-Hump-Camel-Back function, as well as the Gasoline Direct Injection engine steady-state engine mapping problem that motivated this research. The case studies show that the algorithm is effective in delivering quasi-orthogonal space-filling DoEs with good properties even after several MB–MV iterations, while the improvement in model adequacy and accuracy can be monitored by the engineering analyst. The practical importance of this work, demonstrated through the engine case study, is that significant reduction in the effort and cost of testing can be achieved.     

Gait modification and optimization using neural network–genetic algorithm approach: Application to knee rehabilitation

Gait modification strategies play an important role in the overall success of total knee arthroplasty. There are a number of studies based on multi-body dynamic (MBD) analysis that have minimized knee adduction moment to offload knee joint. Reducing the knee adduction moment, without consideration of the actual contact pressure, has its own limitations. Moreover, MBD-based framework that mainly relies on iterative trial-and-error analysis, is fairly time consuming. This study embedded a time-delay neural network (TDNN) in a genetic algorithm (GA) as a cost effective computational framework to minimize contact pressure. Multi-body dynamic and finite element analyses were performed to calculate gait kinematics/kinetics and the resultant contact pressure for a number of experimental gait trials. A TDNN was trained to learn the nonlinear relation between gait parameters (inputs) and contact pressures (output). The trained network was then served as a real-time cost function in a GA-based global optimization to calculate contact pressure associated with each potential gait pattern. Two optimization problems were solved: first, knee flexion angle was bounded within the normal patterns and second, knee flexion angle was allowed to be increased beyond the normal walking. Designed gait patterns were evaluated through multi-body dynamic and finite element analyses.The TDNN-GA resulted in realistic gait patterns, compared to literature, which could effectively reduce contact pressure at the medial tibiofemoral knee joint. The first optimized gait pattern reduced the knee contact pressure by up to 21% through modifying the adjacent joint kinematics whilst knee flexion was preserved within normal walking. The second optimized gait pattern achieved a more effective pressure reduction (25%) through a slight increase in the knee flexion at the cost of considerable increase in the ankle joint forces. The proposed approach is a cost-effective computational technique that can be used to design a variety of rehabilitation strategies for different joint replacement with multiple objectives.     

Optimal power flow of HVDC system using teaching–learning-based optimization algorithm

In this paper, a solution to the optimal power flow (OPF) problem in electrical power networks is presented considering high voltage direct current (HVDC) link. Furthermore, the effect of HVDC link converters on the active and reactive power is evaluated. An objective function is developed for minimizing power loss and improving voltage profile. Gradient-based optimization techniques are not viable due to high number of OPF equations, their complexity and equality and inequality constraints. Hence, an efficient global optimization method is used based on teaching–learning-based optimization (TLBO) algorithm. The performance of the suggested method is evaluated on a 5-bus PJM network and compared with other algorithms such as particle swarm optimization, shuffled frog-leaping algorithm and nonlinear programming. The results are promising and show the effectiveness and robustness of TLBO method.

     

Parameter optimization of modern machining processes using teaching–learning-based optimization algorithm

Modern machining processes are now-a-days widely used by manufacturing industries in order to produce high quality precise and very complex products. These modern machining processes involve large number of input parameters which may affect the cost and quality of the products. Selection of optimum machining parameters in such processes is very important to satisfy all the conflicting objectives of the process. In this research work, a newly developed advanced algorithm named ‘teaching–learning-based optimization (TLBO) algorithm’ is applied for the process parameter optimization of selected modern machining processes. This algorithm is inspired by the teaching–learning process and it works on the effect of influence of a teacher on the output of learners in a class. The important modern machining processes identified for the process parameters optimization in this work are ultrasonic machining (USM), abrasive jet machining (AJM), and wire electrical discharge machining (WEDM) process. The examples considered for these processes were attempted previously by various researchers using different optimization techniques such as genetic algorithm (GA), simulated annealing (SA), artificial bee colony algorithm (ABC), particle swarm optimization (PSO), harmony search (HS), shuffled frog leaping (SFL) etc. However, comparison between the results obtained by the proposed algorithm and those obtained by different optimization algorithms shows the better performance of the proposed algorithm.     

Optimal control of time-varying singular systems using the RK–Butcher algorithm

The problem of optimal control of time-varying linear singular systems with quadratic performance index has been studied using the Runge–Kutta–Butcher algorithm. The results obtained using the Runge–Kutta (RK) method based on the arithmetic mean (RKAM) and the RK–Butcher algorithms are compared with the exact solutions of the time-varying optimal control of linear singular systems. It is observed that the result obtained using the RK–Butcher algorithm is closer to the true solution of the problem. Stability regions for the RKAM algorithm, the single-term Walsh series method and the RK–Butcher algorithms are presented. Error graphs for the simulated results and exact solutions are presented in graphical form to highlight the efficiency of the RK–Butcher algorithm. This algorithm can easily be implemented using a digital computer. An additional advantage of this method is that the solution can be obtained for any length of time for this type of optimal control of time-varying linear singular systems.     

On profile reconstruction of Euler–Bernoulli beams by means of an energy based genetic algorithm

Engineering with Computers - This paper studies the inverse problem related to the identification of the flexural stiffness of an Euler Bernoulli beam to reconstruct its profile starting from...     

Modular product design with grouping genetic algorithm—a case study

Modular products are products that fulfill various functions through the combination of distinct modules. These detachable modules are constructed both according to the maximum physical and functional relations among components and maximizing the similarity of specifically modular driving forces. Accordingly, a non-linear programming is proposed to identify separable modules and simultaneously optimize the number of modules. This paper presents a systematic approach to accomplish modular product design in four major phases. Phase 1 is by means of functional and physical interaction analysis to format a component-to-component correlation matrix. Phase 2 is the exploration of design requirements to evaluate the relative importance of each modular driver. In phase 3, non-linear programming is used to formulate the objective function. In the final phase, a heuristic grouping genetic algorithm is adopted to search for the optimal or near-optimal modular architecture. This process and its application are illustrated by a real case of an electrical consumer product provided by an Original Design Manufacturer. The results demonstrate that the designer could direct a new approach to establish product modules according to the relative importance of modular drivers and the interaction among components.     

Optimization of multiple input–output fuzzy membership functions using clonal selection algorithm

A clonal selection algorithm (CLONALG) inspires from clonal selection principle used to explain the basic features of an adaptive immune response to an antigenic stimulus. It takes place in various scientific applications and it can be also used to determine the membership functions in a fuzzy system. The aim of the study is to adjust the shape of membership functions and a novice aspect of the study is to determine the membership functions. Proposed method has been implemented using a developed CLONALG program for a multiple input–output (MI–O) fuzzy system. In this study, GA and binary particle swarm optimization (BPSO) are used for implementing the proposed method as well and they are compared. It has been shown that using clonal selection algorithm is advantageous for finding optimum values of fuzzy membership functions