Position Update Process Research Articles

Autonomous Underwater Vehicle Trajectory Prediction with the Nonlinear Kepler Optimization Algorithm–Bidirectional Long Short-Term Memory–Time-Variable Attention Model

Autonomous underwater vehicles (AUVs) have been widely used in ocean missions. When they fail in the ocean, it is important to predict their trajectory. Existing methods rely heavily on historical trajectory data while overlooking the influence of the ocean environment on an AUV’s trajectory. At the same time, these methods fail to use the dependency between variables in the trajectory. To address these challenges, this paper proposes an AUV trajectory prediction model known as the nonlinear Kepler optimization algorithm–bidirectional long short-term memory–time-variable attention (NKOA-BiLSTM-TVA) model. This paper introduces opposition-based learning during the initialization process of the KOA and improves the algorithm by incorporating a nonlinear factor into the planet position update process. We designed an attention mechanism layer that spans both time and variable dimensions, called TVA. TVA can extract features from both the time and variable dimensions of the trajectory and use the dependency between trajectory variables to predict the trajectory. First, the model uses a convolutional neural network (CNN) to extract spatial features from the trajectory. Next, it combines a BiLSTM network with TVA to predict the AUV’s trajectory. Finally, the improved NKOA is used to optimize the model’s hyperparameters. Experimental results show that the NKOA-BiLSTM-TVA model has an excellent parameter optimization effect and higher prediction accuracy in AUV trajectory prediction tasks. It also achieves excellent results in ship trajectory prediction.

An oscillatory particle swarm optimization feature selection algorithm for hybrid data based on mutual information entropy

Hybrid data lead to overfitting in machine learning models, which may reduce the accuracy of classification. Feature selection can not only reduce the computational cost of processing hybrid data but also improve the accuracy of classification. The particle swarm optimization (PSO) algorithm has clear advantages in feature selection. This paper presents an oscillatory particle swarm optimization feature selection algorithm for hybrid data based on mutual information entropy. First, a new distance function on the object set of a hybrid information system (HIS) is built, which yields a tolerance relation on this object set. Then, mutual information entropy is presented to measure the uncertainty of the HIS. On this basis, the maximum-relevance and minimal-redundancy model (MRMR model) for the HIS is proposed. Based on the MRMR model, a feature selection algorithm (denoted as MRMR) for the HIS is naturally designed. As the integration of the MRMR model and PSO can effectively explore all possible feature subsets, an oscillatory particle swarm optimization algorithm based on the MRMR model (denoted as OPSO-MRMR) for the HIS is also designed. Moreover, the MRMR model is utilized to define a fitness function that evaluates the quality of particles. The particle position update process is modified by means of a two-order oscillatory equation. Finally, an experimental analysis is conducted to compare the two designed algorithms with five other algorithms. The statistical analysis of classification accuracy and F1 score shows that OPSO-MRMR improves precision by 5.8% and 10.7% compared to the other six algorithms, respectively.

Improved multi-objective grasshopper optimization algorithm and application in capacity configuration of urban rail hybrid energy storage systems

Aiming at addressing problems of poor diversity and ergodicity of initial population, slow convergence speed, and susceptibility to local optima in conventional multi-objective grasshopper optimization algorithm (MOGOA), an improved MOGOA is proposed in this paper. The proposed algorithm is based on Sobol sequence, adaptive social force, cosine parameter c, as well as Levy flight mechanism (SACLMOGOA), where Sobol sequence is adopted to initialize the population, thereby improving the diversity and ergodicity of the initial population. The adaptive social force is proposed to enhance the global exploration ability in the early stage of iteration and the local development ability in the late stage of iteration. A cosine type parameter c is used to ensure sufficient exploration time and rapid convergence of the algorithm during position update process and Levy flight is used to guide some grasshoppers to mutate, enhancing the ability to escape from the local optima and improving the performance and efficiency of the algorithm. The proposed algorithm is tested with ZDT and DTLZ series benchmark test functions to validate its effectiveness, and it is also compared with conventional MOGOA, multi-objective particle swarm optimization, multi-objective gray Wolf, and multi-objective jellyfish algorithms. The simulation results demonstrate that the proposed algorithm outperforms other algorithms in terms of inverse generational distance (IGD), spread (SP), maximum spread (MS), run time and Wilcoxon rank sum test. Furthermore, the proposed algorithm is successfully applied to the capacity configuration of the urban rail hybrid energy storage systems (HESS) of Changsha Metro Line 1 in China, reducing the traction network voltage fluctuations by 3.3 % and 2.2 % compared to no HESS capacity configuration optimization, and by 14 % and 5.7 % compared to no HESS during train starting and breaking, respectively. While achieving the goal of energy-saving and voltage stabilization, the cost of the hybrid energy storage systems is minimized as well. All of these have demonstrated SACLMOGOA is an effective tool for solving complex multi-objective optimization problems in engineering.

Continuous Reactor Temperature Control with Optimized PID Parameters Based on Improved Sparrow Algorithm

To address the problems of strong coupling and large hysteresis in the temperature control of a continuously stirred tank reactor (CSTR) process, an improved sparrow search algorithm (ISSA) is proposed to optimize the PID parameters. The improvement aims to solve the problems of population diversity reduction and easy-to-fall-into local optimal solutions when the traditional sparrow algorithm is close to the global optimum. This differs from other improved algorithms by adding a new Gauss Cauchy mutation strategy at the end of each iteration without increasing the time complexity of the algorithm. By introducing tent mapping in the sparrow algorithm to initialize the population, the population diversity and global search ability are improved; the golden partition coefficient is introduced in the explorer position update process to expand the search space and balance the relationship between search and exploitation; the Gauss Cauchy mutation strategy is used to enhance the ability of local minimum value search and jumping out of local optimum. Compared with the four existing classical algorithms, ISSA has improved the convergence speed, global search ability and the ability to jump out of local optimum. The proposed algorithm is combined with PID control to design an ISSA-PID temperature controller, which is simulated on a continuous reactor temperature model identified by modeling. The results show that the proposed method improves the transient and steady-state performance of the reactor temperature control with good control accuracy and robustness. Finally, the proposed algorithm is applied to a semi-physical experimental platform to verify its feasibility.

A Novel Hybrid Whale-Chimp Optimization Algorithm for Structural Damage Detection

Damage detection of structures based on swarm intelligence optimization algorithms is an effective method for structural damage detection and key parts of the field of structural health monitoring. Based on the chimp optimization algorithm (ChOA) and the whale optimization algorithm, this paper proposes a novel hybrid whale-chimp optimization algorithm (W-ChOA) for structural damage detection. To improve the identification accuracy of the ChOA, the Sobol sequence is adopted in the population initialization stage to make the population evenly fill the entire solution space. In addition, to improve the local search ability of the traditional ChOA, the bubble-net hunting mechanism and the random search mechanism of the whale optimization algorithm are introduced into the position update process of the ChOA. In this paper, the validity and applicability of the proposed method are illustrated by a two-story rigid frame model and a simply supported beam model. Simulations show that the presented method has much better performance than the ChOA, especially in dealing with multiple damage detection cases. The W-ChOA has good performance in both overcoming misjudgment and improving computational efficiency, which should be a preferred choice in adoption for structural damage detection.

Fault monitoring and diagnosis of high-pressure heater system based on improved particle swarm optimization and probabilistic neural network

The high-pressure heater system is an important part of the return heat system of thermal power units, which can significantly reduce the boiler fuel consumption and is of great significance to the safe and economic operation of the units. Taking into consideration the issues that the high-pressure heater system data has strong non-linear characteristics and the fault diagnosis accuracy is low, this paper proposes a hybrid model-based fault monitoring and diagnosis method for a high-pressure heater system. Firstly, an improved particle swarm optimization algorithm (IEDPSO) is proposed. A differential evolution operation is introduced to enhance particle diversity, and the inertia weight coefficients and learning factor parameters are improved to optimize the particle position and velocity update process. The problem that PSO tends to fall into local optimum at the late stage of iterative optimization search is solved. Numerical simulation experiments demonstrate that IDEPSO has high convergence speed and accuracy in the optimization process of the test function. Secondly, a fault monitoring and diagnosis method based on a hybrid kernel principal component analysis (KPCA)-IDEPSO-probabilistic neural network (PNN) model is proposed. Non-linear features are extracted using KPCA for fault monitoring. The IDEPSO algorithm is used to iteratively find the best PNN to improve the fault diagnosis accuracy. Simulation experiments prove that compared with the traditional PNN model, the fault diagnosis accuracy of the KPCA-IDEPSO-PNN model is improved by 4.9% and the number of fault misclassifications is reduced by 34, effectively improving the fault diagnosis accuracy of the high-pressure heater system and ensuring the safe and stable operation of thermal power units.

Application of IEHO–BP neural network in forecasting building cooling and heating load

Countering the issue of low optimization accuracy and poor stability of the Elephant Herding Optimization (EHO) algorithm when solving multi-dimensional nonlinear complex problems, putting forward an improved Elephant Herding Optimization (IEHO) algorithm. The algorithm improves the accuracy of EHO algorithm optimization by chaosing the initial solution, adding dynamic influence factors, Levy flight operators and boundary mutation operators in the position update process. Standard functions are used for test experiments, and the results indicate that the introduction of improved strategies can effectively improve the accuracy and stability of the EHO algorithm when solving optimization problems. In view of the performance of the IEHO algorithm in function optimization, combining it with the BP neural network, proposing the IEHO–BP neural network algorithm, and using new algorithm to forecasting the building cooling and heating load. The experimental results show that compared with other group intelligence optimization algorithms, the output results of the cooling and heating load forecasting model based on the IEHO–BP neural network algorithm are more accurate and less oscillating.

Fully informed ABC algorithm for large scale job shop scheduling problem

The large-scale job-shop scheduling problem (LSJSSP) is a complex scheduling problem. Previously, although the nature-inspired algorithm, specially the swarm intelligence (SIA) based algorithms have been efficiently applied to solve the LSJSSP, finding the best solution for LSJSSP instances remains a challenging task. Therefore, in this paper, a novel SIA is applied to solve the 105 LSJSSP instances. The selected SIA is a fully informed artificial bee colony (FABC) algorithm. The FABC algorithm is a variant of the ABC algorithm in which the position update process is inspired from the GABC. In the FABC, the onlooker bee process of the ABC strategy is modified and designed such that the new position of the solution search agent is obtained while learning from all the nearby agents. The results obtained by the FABC are compared with the strategies available in the literature. The results analysis shows that the proposed approach to solving LSJSSP is competitive in the field of SIA.

A VMD–CISSA–LSSVM Based Electricity Load Forecasting Model

Accurate power load forecasting has an important impact on power systems. In order to improve the load forecasting accuracy, a new load forecasting model, VMD–CISSA–LSSVM, is proposed. The model combines the variational modal decomposition (VMD) data preprocessing method, the sparrow search algorithm (SSA) and the least squares support vector machine (LSSVM) model. A multi-strategy improved chaotic sparrow search algorithm (CISSA) is proposed to address the shortcomings of the SSA algorithm, which is prone to local optima and a slow convergence. The initial population is generated using an improved tent chaotic mapping to enhance the quality of the initial individuals and population diversity. Second, a random following strategy is used to optimize the position update process of the followers in the sparrow search algorithm, balancing the local exploitation performance and global search capability of the algorithm. Finally, the Levy flight strategy is used to expand the search range and local search capability. The results of the benchmark test function show that the CISSA algorithm has a better search accuracy and convergence performance. The volatility of the original load sequence is reduced by using VMD. The optimal parameters of the LSSVM are optimized by the CISSA. The simulation test results demonstrate that the VMD–CISSA–LSSVM model has the highest prediction accuracy and stabler prediction results.

Archimedean spiral based artificial bee colony algorithm

Swarm intelligence techniques are popular meta-heuristics which are developed to solve very complex problems that are not decipherable using traditional optimization approaches. In this class, artificial bee colony is latest and efficient algorithm that is able to solve complex problems. During solution search process it perform exploration in the early iterations, while should utilize the identified area in later stage. By analyzing the ABC, it is clear that the position update process depends on the difference of two random vector multiplied by a random component. So the step size of ABC is exceedingly hinge on these arbitrary components that leads to skipping of good solutions. For that reason, in this paper, Archimedean Spiral inspired Local Search (ASLS) algorithm is united with ABC and the new algorithm is labelled as Archimedean Spiral based ABC (ASABC) algorithm. In ASABC, in the current swarm only good solutions get chance to exploit the nearby search space using ASLS local search approach in every iteration. To demonstrate the performance of ASABC, experiment performed over 10 recognized benchmarks and compared with basic ABC, Best-so-far ABC and Modified ABC. Outcomes prove that ASABC algorithm may be considered as a viable algorithm for optimization problems.

Effective competency based differential evolution algorithm

The DE algorithm is considered as an efficient algorithm in the field of evolutionary algorithms. In case of DE the solution search process is a combination of evolutionary (evolution of population) and swarm intelligence (position update of individual) search process. In DE, the diversification and convergence of the population is controlled by the crossover rate (CR), the scale factor (F) and the vector differences of three randomly selected individuals. In DE algorithm, every solution is given equal chance to take part in the solution search and in case of stagnation; it is difficult to get out from this situation. Therefore, a competency based position update process is integrated in DE to boost the speed of convergence in addition to the diversification ability of the algorithm. The accuracy, efficiency, robustness, and reliability of the proposed algorithm, namely efficient competency based DE (ECDE) are analyzed over a set of 20 benchmark problems with diverse characteristics. Results are compared with DE and its two recent variants, namely FBDE, FSADE, and other algorithms, namely ABC and PSO.

Truss Structure Optimization Based on Improved Chicken Swarm Optimization Algorithm

To improve the efficiency of the structural optimization design in truss calculation, an improved chicken swarm optimization algorithm was proposed for truss structure optimization. The chicken swarm optimization is a novel swarm intelligence algorithm. In the basic chicken swarm optimization algorithm, the concept of combining chaos strategy and reverse learning strategy was introduced in the initialization to ensure the global search ability. And the inertia weighting factor and the learning factor were introduced into the chick position update process, so as to better combine the global and local search. Finally, the overall individual position of the algorithm was optimized by the differential evolution algorithm. The improved algorithm was tested by multipeak function and applied to the truss simulation experiment. The study provided a new method for the truss structure optimization.

Modified global best artificial bee colony for constrained optimization problems

Artificial Bee Colony (ABC) is one of the most popular nature inspired optimization algorithms. Recently, a variant of ABC, Gbest-guided ABC (GABC) was proposed. GABC was verified to perform better than ABC, in terms of efficiency and reliability. In the position update process of GABC, Gbest (the best individual in the swarm) individual influences the movement of the swarm. This movement may create a cluster around the Gbest individual which further leads to the premature convergence, particularly for constrained optimization problems. This paper presents a modification in GABC for constrained optimization problems. GABC is modified in both employed and onlooker bee phases by incorporating the concept of fitness probability based individual movement. The modified GABC is tested over 20 constrained benchmark problems and applied to solve 3 engineering design problems. Optimal power flow problem has also been solved using modified GABC to check the efficiency of the proposed algorithm.

Artificial bee colony algorithm with an adaptive greedy position update strategy

Artificial bee colony (ABC) is a recent swarm intelligence algorithm. There have been some greedy ABC variants developed to enhance the exploitation capability, but greedy variants are usually less reliable and may cause premature convergence, especially without proper control on the greediness degree. In this paper, we propose an adaptive ABC algorithm (AABC), which is characterized by a novel greedy position update strategy and an adaptive control scheme for adjusting the greediness degree. The greedy position update strategy incorporates the information of top t solutions into the search process of the onlooker bees. Such a greedy strategy is beneficial to fast convergence performance. In order to adapt the greediness degree to fit for different optimization scenarios, the proposed adaptive control scheme further adjusts the size of top solutions for selection in each iteration of the algorithm. The adjustment is based on considering the current search tendency of the bees. This way, by combining the greedy position update process and the adaptive control scheme, the convergence performance and the robustness of the algorithm can be improved at the same time. A set of benchmark functions is used to test the proposed AABC algorithm. Experimental results show that the components of AABC can significantly improve the performance of the classic ABC algorithm. Moreover, the AABC performs better than, or at least comparably to, some existing ABC variants as well as other state-of-the-art evolutionary algorithms.

Parallel social spider clustering algorithm for high dimensional datasets

The Social-Spider Optimization (SSO) is one of the recently developed swarm intelligence. It is inspired from the social behavior of spiders living in huge colonies. In this manuscript, a parallel version of this algorithm is formulated and termed as P-SSO by making a position update process of spiders (female, dominant and non-dominant male) running simultaneously. Simulation studies on cluster analysis of benchmark high-dimensional datasets using proposed P-SSO are found to be nearly 10 times computationally faster than the original version of SSO. Comparative analysis with other standard parallel version algorithms like Adaptive Parallel Particle Swarm Optimization (PPSO), Real Coded Parallel Genetic Algorithm (RCPGA) and K-means reveals the superior clustering accuracy of the proposed method. The designed algorithm is also tested on real life application where multi-spectral image segmentation is formulated as a clustering problem. The images are taken from NASA landsat 8. It covers an area of 200km of Northwest Chennai obtained before and after flood conditions. This is done to analyze the flood severity. The overall accuracy of P-SSO is highest among all the methods. Also, in case of detection of water flooded areas the producer's accuracy is 76.89% which is two times better than K-means.

Fitness based Differential Evolution

Differential Evolution (DE) is a well known and simple population based probabilistic approach for global optimization. It has reportedly outperformed a few Evolutionary Algorithms and other search heuristics like Particle Swarm Optimization when tested over both benchmark and real world problems. But, DE, like other probabilistic optimization algorithms, sometimes exhibits premature convergence and stagnates at suboptimal point. In order to avoid stagnation behavior while maintaining a good convergence speed, a new position update process is introduced, named fitness based position update process in DE. In the proposed strategy, position of the solutions are updated in two phases. In the first phase all the solutions update their positions using the basic DE and in the second phase, all the solutions update their positions based on their fitness. In this way, a better solution participates more times in the position update process. The position update equation is inspired from the Artificial Bee Colony algorithm. The proposed strategy is named as Fitness Based Differential Evolution ( $$FBDE$$ ). To prove efficiency and efficacy of $$FBDE$$ , it is tested over 22 benchmark optimization problems. A comparative analysis has also been carried out among proposed FBDE, basic DE, Simulated Annealing Differential Evolution and Scale Factor Local Search Differential Evolution. Further, $$FBDE$$ is also applied to solve a well known electrical engineering problem called Model Order Reduction problem for Single Input Single Output Systems.