Corrosion Simulation and Optimization of Sacrificial Anode Protection of a Buried Pipeline Using Teaching Learning Based Optimization (TLBO) Algorithm

Teaching learning based optimization (TLBO) algorithm is a distinguished nature-inspired population-based meta-heuristic, which is basically designed for unconstrained optimization. TLBO mimics teaching learning process through which learners acquire knowledge from their teachers, and improve their results/grades, accordingly. Stochastic ranking (SR) is a constrained handling technique (CHT), which produces greediness among solutions to improve their fitness values and feasibility. Violation constraint handling (VCH) technique produces more feasibility among the existing superiority of feasibility CHTs due to its additional factor of ranking based on the number of constraints violated (NCV). This work brings in a new variant of SR, namely hybrid stochastic ranking (HSR), which combines SR and VCH. For constrained optimization, the integration of some CHT with TLBO is essential. In this paper, HSR is integrated with TLBO and a new constrained version of TLBO called HSR-TLBO is designed. The efficiency of HSR-TLBO is checked on constrained test functions of the suit CEC 2017. The experimental results show that HSR-TLBO got prominent position when compared and ranked with the top four papers and our two newly designed constrained variants of TLBO, MSR-TLBO and MVCH-TLBO, based on the provided budget and ranking criteria of the mentioned suit.

The Teaching Learning Based Optimization (TLBO) algorithm simulates the knowledge-transfer process between teacher and learners as well as between peer learners. Although TLBO has been already successfully applied to both constrained and unconstrained engineering optimization problems, it sometimes prematurely converges toward local optima, especially in high dimensional, multimodal, or deceptive fitness landscapes. We therefore propose to further characterize the limitations of TLBO by investigating its performance on different benchmarks featuring both stationary, to establish a baseline, but especially non-stationary fitness landscapes. The results are then compared with a state of the art population-based optimization algorithm (Differential Evolution - DE) and its variants Self Adaptive Differential Evolution (jDE) in order to establish the suitability of TLBO on such landscapes. We found that TLBO exhibits a pronounced imbalance in its exploration vs. exploitation tradeoff that prevents it from maintaining a diversified population. It is well known that maintaining diversity as the population converges, and more generally balancing the exploration versus exploitation tradeoff, are both essential considerations in any population-based optimization technique. This is especially true for non-trivial problems where premature convergence to local optima is more likely. We therefore also proposed a novel TLBO variant that better manages population diversity and is therefore more suitable for dynamic optimization applications. We found that the resulting DynTLBO algorithm showed significant performance improvements on commonly used benchmarks.

Purpose This paper aims to deal with the development of a newly improved version of teaching learning based optimization (TLBO) algorithm. Design/methodology/approach Random local search part was added to the classic optimization process with TLBO. The new version is called TLBO algorithm with random local search (TLBO-RLS). Findings At first step and to validate the effectiveness of the new proposed version of the TLBO algorithm, it was applied to a set of two standard benchmark problems. After, it was used jointly with two-dimensional non-linear finite element method to solve the TEAM workshop problem 25, where the results were compared with those resulting from classical TLBO, bat algorithm, hybrid TLBO, Nelder–Mead simplex method and other referenced work. Originality value New TLBO-RLS proposed algorithm contains a part of random local search, which allows good exploitation of the solution space. Therefore, TLBO-RLS provides better solution quality than classic TLBO.

After the teaching–learning-based optimization (TLBO) algorithm was proposed, many improved algorithms have been presented in recent years, which simulate the teaching–learning phenomenon of a classroom to effectively solve global optimization problems. In this paper, a cyclical non-linear inertia-weighted teaching–learning-based optimization (CNIWTLBO) algorithm is presented. This algorithm introduces a cyclical non-linear inertia weighted factor into the basic TLBO to control the memory rate of learners, and uses a non-linear mutation factor to control the learner’s mutation randomly during the learning process. In order to prove the significant performance of the proposed algorithm, it is tested on some classical benchmark functions and the comparison results are provided against the basic TLBO, some variants of TLBO and some other well-known optimization algorithms. The experimental results show that the proposed algorithm has better global search ability and higher search accuracy than the basic TLBO, some variants of TLBO and some other algorithms as well, and can escape from the local minimum easily, while keeping a faster convergence rate.

An improved TLBO based economic dispatch of power generation through distributed energy resources considering environmental constraints

Teaching Learning Based Optimization (TLBO) is one of the non-traditional techniques to simulate natural phenomena into a numerical algorithm. TLBO mimics teaching learning process occurring between a teacher and students in a classroom. A parameter named as teaching factor, TF, seems to be the only tuning parameter in TLBO. Although the value of the teaching factor, TF, is determined by an equation, the value of 1 or 2 has been used by the researchers for TF. This study intends to explore the effect of the variation of teaching factor TF on the performances of TLBO. This effect is demonstrated in solving structural optimization problems including truss and frame structures under the stress and displacement constraints. The results indicate that the variation of TF in the TLBO process does not change the results obtained at the end of the optimization procedure when the computational cost of TLBO is ignored.

This research presents a comparative analysis of six metaheuristic algorithms such as Genetic Algorithm (GA), Simulated Annealing (SA), Particle Swarm Optimisation (PSO), Teaching-Learning-Based Optimisation (TLBO), Cohort Intelligence (CI), and JAYA Algorithm focused on optimising the wear behaviour of LPBF-printed AlSi10Mg parts under elevated temperatures. The potential of each algorithm to optimise the process factors and reduce wear loss and Specific Wear Rate (SWR) was used to assess its performance. SEM analysis reveals that the LPBF-processed AlSi10Mg alloy has a refined microstructure, with a predominantly α-Al matrix and finely dispersed silicon particles. It attains a high degree of compaction and minimal porosity with density close to the theoretical value. EDS mapping shows the presence of aluminium, silicon, magnesium, and copper, with silicon predominantly in eutectic form. X-ray diffraction analysis reveals that there is an aluminium phase arranged in a face-centered cubic structure and magnesium silicide. The results also indicated that PSO, TLBO, and JAYA outperformed other algorithms and that TLBO had the best result in terms of accuracy. The wear loss obtained by TLBO was 0.044924 grams, the least among other methods, with the minimal experimental deviation of 6.21%, which shows that the TLBO technique is capable of optimising the wear resistance of LPBF-printed AlSi10Mg parts. PSO, TLBO, and JAYA were able to obtain the lowest SWR values, setting them apart from the other algorithms in terms of their performance. The minimum experimental deviation of 0.91% was obtained by TLBO, which was the most accurate predictor. It was found that the use of CI to achieve the wear resistance was more effective than through TLBO. Abrasion and adhesion wear mechanisms were minimised by TLBO and resulted in significantly lower wear loss and SWR. On the other hand, CI gave rise to more aggressive wear. The use of TLBO to identify optimal factor combinations successfully reduced material removal while enhancing the tribological performance of the AlSi10Mg components, especially under high-temperature conditions. This indicates that TLBO effectively enhances the wear-resisting properties of AlSi10Mg prints.

The teaching learning based optimization(TLBO) algorithm requires few parameters and has a simple operating process comparing with some other optimization algorithms. However, the original TLBO has a low convergence speed and is easy to have a premature convergence. To reinforce the global performance of the algorithm, a novel hybrid teaching-learning optimization (HTLBO) is proposed. Firstly, an opposing-based initializing strategy is used to enhance the structure of the initial distribution. Secondly, the proposed algorithm combines the local search with the teaching phase of TLBO in order to improve the local search ability of HTLBO. A special teaching process is employed to some specific students to improve the convergence speed. HTLBO is tested on benchmark functions and the experimental results show that HTLBO has better global optimization performances than the comparative algorithms.

Teaching Learning Based Optimization (TLBO) algorithm simulate the teaching learning peculiarity of a classroom to solve multidimensional, linear and nonlinear problems with appreciable efficiency. In order to accelerate the execution time of software implementation, the TLBO algorithm is implemented on hardware. Then the TLBO hardware is developed as TLBO Intellectual Property and it is interfaced as a peripheral to the System on Chip platform. We compared the performance of the floating point TLBO IP is realized by solving the benchmark functions, results 183–224X times faster than the software implementation of the same algorithm. As a case study, the same TLBO IP is used to solve the spectrum allocation problem by optimizing Max-Sum-Reward (MSR) function and it results 69–78X times faster than the software implementation of the same algorithm.

In this work Advanced Teaching-Learning-Based Optimization algorithm (ATLBO) is proposed to solve the optimal reactive power problem. Teaching-Learning-Based Optimization (TLBO) optimization algorithm has been framed on teaching learning methodology happening in classroom. Algorithm consists of “Teacher Phase”, “Learner Phase”. In the proposed Advanced Teaching-Learning-Based Optimization algorithm non-linear inertia weighted factor is introduced into the fundamental TLBO algorithm to manage the memory rate of learners. In order to control the learner’s mutation arbitrarily during the learning procedure a non-linear mutation factor has been applied. Proposed Advanced Teaching-Learning-Based Optimization algorithm (ATLBO) has been tested in standard IEEE 14, 30 bus test systems and simulation results show the proposed algorithm reduced the real power loss effectively.

In This Paper, an optimum tuning of PID Controller is proposed. A Linear Brushless DC motor is known for higher efficiency a lower maintenance. A newly developed algorithm named, teaching learning based optimization algorithm is applied for the PID Controller tuning of Brushless Linear DC Motor. This algorithm is inspired by the teaching learning process and it works on the effect of influence of a teacher on the output of the learners in a class. Teaching -- Learning-Based Optimization (TLBO) algorithms simulate the teaching -- learning phenomenon of a classroom to solve multidimensional, linear and nonlinear problems with appreciable efficiency. TLBO is population based method. The performance of TLBO algorithm compared Mehdi nasri et.at. Realization of TLBO based PID controller for BLDC motor is economic and easily implemented.

Reservoir operation and management are complex engineering problems, due to the stochastic nature of inflow, various demands and as well as tailwater in the downstream. The complexity increases when the number of reservoirs gets increased such as multi-reservoir system or chain system. To obtain optimal operation in such condition become more difficult. It requires powerful optimization algorithm to solve aforesaid problems. Teaching Learning Based Optimization (TLBO) algorithm and Jaya Algorithm (JA) are recently developed advanced optimization techniques a novel approach comparatively simple, easy, and robust. The main advantages of these algorithms are it only requires the common control parameters such as number of iterations and population size. In the present study, three different benchmark problems were evaluated to check the applicability and performance of TLBO and JA in multi-reservoir operation problems. The benchmark problems are the discrete time four-reservoir operation (DFRO), the continuous time four-reservoir operation (CFRO), and the ten-reservoir operation (TRO). The results from the TLBO and JA are compared with different approaches from the literature. The optimal net benefits obtained from JA for DFRO, CFRO and TRO problems are 401.44, 308.40 and 1194.59, respectively, and that of TLBO algorithm are 401.33, 308.30 and 1194.44, respectively. It is found that both JA and TLBO algorithms provided a satisfactory solution as other optimization techniques, from literature. In conclusion, JA outperformed over TLBO.

Transient stability constrained optimal power flow (TSC-OPF) is a non-linear optimization problem which is not easy to deal directly because of its huge dimension. In order to solve the TSC-OPF problem efficiently, a relatively new optimization technique named teaching learning based optimization (TLBO) is proposed in this paper. TLBO algorithm simulates the teaching–learning phenomenon of a classroom to solve multi-dimensional, linear and nonlinear problems with appreciable efficiency. Like other nature-inspired algorithms, TLBO is also a population-based method and uses a population of solutions to proceed to the global solution. The authors have explained in detail, the basic philosophy of this method. In this paper, the authors deal with the comparison of other optimization problems with TLBO in solving TSC-OPF problem. Case studies on IEEE 30-bus system WSCC 3-generator, 9-bus system and New England 10-generator, 39-bus system indicate that the proposed TLBO approach is much more computationally efficient than the other popular methods and is promising to solve TSC-OPF problem.

Transient stability constrained optimal power flow (TSC-OPF) is a non-linear optimization problem which is not easy to deal directly because of its huge dimension. In order to solve the TSC-OPF problem efficiently, a relatively new optimization technique named teaching learning based optimization (TLBO) is proposed in this paper. TLBO algorithm simulates the teaching–learning phenomenon of a classroom to solve multi-dimensional, linear and nonlinear problems with appreciable efficiency. Like other nature-inspired algorithms, TLBO is also a population-based method and uses a population of solutions to proceed to the global solution. The authors have explained in detail, the basic philosophy of this method. In this paper, the authors deal with the comparison of other optimization problems with TLBO in solving TSC-OPF problem. Case studies on IEEE 30-bus system WSCC 3-generator, 9-bus system and New England 10-generator, 39-bus system indicate that the proposed TLBO approach is much more computationally efficient than the other popular methods and is promising to solve TSC-OPF problem.

Lately, the world is looking forward to replacing fossil fuels with renewable energy resources. Photovoltaic (PV) is benefited among renewable energies by its simple design, easy fitting, and fast expansion. For proper selection of controller gains for the PV system's control unit, this paper introduces a new hybrid optimization algorithm. The proposed optimization technique is applied to a PV system to enhance its performance under dynamic irradiance. The introduced hybrid optimization approach includes two optimization algorithms which are Teaching Learning Based Optimization (TLBO) and Equilibrium Optimizer (EO). Moreover, this paper presents a comparison with different optimization algorithms (Harmony Search (HS), Teaching Learning Based Optimization (TLBO), Cuttlefish Algorithm (CFA), and Emperor Penguin Optimizer (EPO)) to ensure the superiority of the newly proposed hybrid technique. The results display that the introduced TLBO-EO reduced the maximum overshoot by 30% and the steady-state error by 93% when compared to other techniques.