Display omitted
•A novel grey forecasting method is proposed to predict the production and sales of China’s new energy vehicles.•Accumulation and translation transformations are introduced into the ...grey buffer operator.•A genetic algorithm is used to optimise the parameters of the new operator to ensure high-precision prediction.•The proposed method exhibits much higher prediction accuracy than those of the classical grey forecasting methods.
In recent years, under a series of policy shocks, the production and sales of new energy vehicles in China show the characteristics of trend mutation and non-smoothness. In order to forecast the production and sales of new energy vehicles in China, an optimised grey buffer operator is proposed by introducing accumulation and translation transformations. Meanwhile, a genetic algorithm is employed to ascertain its optimum parameters. Forecasting results indicate that the optimised buffer operator can significantly improve the adaptability of the grey model to the production and sales data of new energy vehicles in China, and exhibits much higher prediction accuracy than those of the classical buffer operator and grey model. Besides, the prediction results show that the production and sales of China’s new energy vehicles will continue to grow from 2018 to 2020, with an average annual growth rate of 27.53% and 30.49%, respectively.
Display omitted
•An intelligent modelling framework is proposed for mechanical properties of CPB.•This framework combines machine learning (ML) algorithms and genetic algorithm.•1077 UCS tests and ...231 UTS tests were conducted to prepare dataset.•The performance of three advanced ML algorithms was verified and compared.•A software, the IMB, was developed for a wider application of this framework.
The mechanical properties of cemented paste backfill (CPB) are particularly important for its application in the minerals industry. In practice, a large number of cumbersome and time-consuming experiments are required to generate the design data. To facilitate the CPB design, this study proposes an intelligent modelling framework for the mechanical properties prediction using machine learning (ML) algorithms and genetic algorithm (GA). Three advanced ML algorithms, including decision tree (DT), gradient boosting machine (GBM), and random forest (RF), were used and compared for the mechanical properties modelling while GA was used for the hyper-parameters tuning. A total of 1077 uniaxial compressive strength (UCS) tests and 231 uniaxial tensile strength (UTS) tests were performed for the dataset preparation. Mechanical properties evaluated were the UCS, the yield strength (YS), the Young’s modulus (E) and the UTS. Influencing variables for these mechanical properties were chosen to be the physical and chemical characteristics of tailings, the cement-tailings ratio, the solids content, and the curing time. The results show that GA was efficient in the hyper-parameters tuning of the evaluated ML algorithms. The GBM was a good first ML algorithm for the mechanical properties modelling with high accuracy (correlation coefficients between predicted and experimental properties were 0.963, 0.887, 0.866 and 0.899 for UCS, YS, E and UTS respectively). Based on the results, a user-friendly software package, named the intelligent mining for backfill (IMB), was developed in python programming for a wider application in the minerals industry. The proposed modelling framework and the IMB will be useful for CPB design by saving time, reducing trial tests and cutting costs.
Evaluation and prediction of displacement by specific models help in forecasting geo-hazards. Among the various available predictive tools, Least Square Support Vector Machines (LSSVM) model ...optimized with Genetic Algorithm, namely GA-LSSVM, is commonly used to empirically forecast landslide displacement due to its capability of processing non-linear complex systems. Another improved hybrid model composed of Double Exponential Smoothing (DES) and LSSVM considers measured displacement and precipitation time series to estimate the one-step ahead displacement evolution of rain-induced landslide. Here, the modelling process and accuracy of these two models are presented, and their predictive performances are evaluated by the root mean squared error (RMSE), mean absolute percentage error (MAPE), accuracy factor (AF), and correlation coefficient (R). A slowly-moving landslide on gently dipping rocky slope located in Sichuan Province of China was chosen as the case study for its deformation triggered by intense seasonal rainfall. The application results indicated that both GA-LSSVM and DES-LSSVM models were suitable for accurately predicting the landslide displacement on the basis of precipitation and displacement observations. Furthermore, comparison results show that DES-LSSVM model can provide the better predictive accuracy, with RMSE and MAPE values of 0.059mm and 0.004%, respectively.
•A hybrid model is proposed to predict displacement of rainfall-triggered landslide.•It includes Least Square Support Vector Machines and Double Exponential Smoothing.•Hodrick-Prescott filter decomposes displacement into periodic and trend components.•The models show high accuracy.
Abstract
At present, the construction of logistics parks has become an indispensable part of the modern logistics system. Scientific and reasonable layout planning of the logistics parks not only ...effectively saves logistics costs, but also promotes the efficient operation of the entire logistics. This article uses a combination of qualitative analysis and quantitative analysis to analyze the layout structure of the functional areas, build a multi-objective mathematical model with the largest degree of adjacency and the smallest transportation cost, and set the functional blocks in horizontal and vertical modes to make the layout more rational, Using genetic algorithm to solve the model with Matlab software, and verify the rationality and effectiveness of the model through examples, providing a new idea for the layout of modern logistics parks.
Intrusion detection is the identification of unauthorized access of a computer network. This paper proposes a novel algorithm for a network intrusion detection system (NIDS) using an improved feature ...subset selected directly by a genetic algorithm (GA)-based exhaustive search and fuzzy C-means clustering (FCM). The algorithm identifies the bagging (BG) classifier and the convolutional neural network (CNN) model as an effective extractor by implementing the GA in combination with 5-fold cross validation (CV) to select the CNN model structure. The deep feature subset extracted by the selected CNN model is put into the BG classifier to validate the performance with the 5-fold CV. The high quality feature set obtained by the three-layered feature construction using the GA, FCM, CNN extractor, and a hybrid CNN and BG learning method significantly improves the final detection performance. Moreover, the highly reliable validation performance results achieved by the 5-fold CV procedure for the proposed algorithm imply a well-fitted application in a practical computer network environment NIDS.
•The feature quality is improved significantly by the three-layered feature construction including feature selection, feature improvement, and deep feature extraction. The GA is employed to select the most informative feature subset, which is processed by the Fuzzy C-means Clustering to compute additional features. The GA is also used to select the best CNN structures using features selected by the feature selection and feature improvement. The selected CNN models, known as the extractors, then generate deep features, which are put into the BG classifier.•The final detection performance of the proposed algorithm is relatively high by the utility of the hybrid learning method of the CNN and BG classifier.•Avoidance of the overfitting problem and better reliable performance results are obtained by implementation of the 5-folds cross validation procedure for feature selection, CNN model selection, and validation of the development method in this work.
•Design of electrostatic lenses with genetic algorithms and swarm optimisation.•Calculation of lens aberrations and spot sizes by differential algebra method.•Evaluation of optimisation outcomes from ...randomly generated lens configurations.•Optimisation of a column comprising two lenses and a Wien filter using genetic algorithms.
Genetic algorithm (GA) and particle swarm optimisation (PSO) techniques have been integrated with the differential algebra (DA) method in charged particle optics to optimise an Einzel lens. The DA method is a robust and efficient tool for the calculation of aberration coefficients of electrostatic lenses, which makes use of nonstandard analysis for ray tracing a particle as it is subjected to the field generated by a lens. In this study, initial populations of lenses with random geometrical configurations are generated. These initial populations are then subjected to GA and PSO algorithms to alter the geometry of each lens for a set number of iterations. The lens performance is evaluated by calculating the spot size using the aberrations coefficients up to third-order generated by the DA method. Moreover, a focusing column comprising two lenses and a Wien filter was optimised using GA method.
•Parallel PV/BSSs are integrated with the grid using a VSG control.•The VSG control is utilizing an ADC for the system frequency regulation.•GA optimization is used to find the optimized values for ...VSG control parameters.•Three different case studies including an IEEE 14 bus system is utilized.
The future power system is developing to an inverter-based system from a machine dominated power system due to a large integration of renewable energy sources (RESs). Lack of inertial part and intermittency of the RESs causes frequency instability in the power system. The virtual synchronous generator (VSG) development has been made to add inertial control to the power system for controlling the frequency deviation caused by the integration of the photovoltaic system. The VSG system comprised of power electronics components having a droop control mechanism like the conventional synchronous generator, which provides the necessary frequency stability to the power system. In this paper, three parallel VSG based photovoltaic systems integrated with battery storage systems are used to analyze the frequency response and its stability. Moreover, an advanced genetic algorithm optimization method is used to get the optimal values of parameters of the droop controller used in VSG. Furthermore, two different cases with respect to variation in supply and load power of the system are analyzed in detail. Additionally, an IEEE 14 bus system is utilized to validate the proposed system in MATLAB/Simulink. Evident improvements are observed in the simulation results presented through the suggested GA based VSG control technique.
This paper studies a method that uses genetic algorithm to simultaneously optimize the number and weights of Back Propagation (BP) neural network neurons to predict the ship's trajectory, so as to ...accurately predict the ship's trajectory. The trajectory of the ship can be predicted by the neural network, but the selection of the setting parameters of the neural network requires rich experience and a large amount of attempts. In this study, the genetic algorithm (GA) is used to optimize the structure and weights of the neural network at the same time, avoiding the manual setting of parameters and improving the accuracy of the neural network prediction.
Multi-band metasurface filters are becoming increasingly pivotal in high-capacity communication technologies. Traditional methods for designing metasurface structures, to date, have relied on ...empirical approaches to obtain target electromagnetic responses, thereby suffering from low efficiency. Here, we demonstrate an advanced approach for the inverse design of a multi-band metasurface filter, which consists of a multi-objective genetic algorithm (MOGA) in tandem with equivalent circuit model (ECM) analysis. This integration converts specific frequency response requirements into ECM parameter constraints, significantly streamlining the metasurface design and optimization process and offering superior solutions. Using this inverse design method, we theoretically propose a dual-bandpass metasurface filter which can exhibit transmission passbands in any two adjacent frequency ranges among the X-, Ku-, and K-bands. Further, numerical simulations validate the performances of the proposed device, which show great agreement with MOGA-based predictions. Our results pave the way to the effective inverse design of multi-passband metasurface filters which are useful in many applications, such as microwave filters, radar and satellite communication systems, and radio frequency identification devices.
•A novel methodology combining MOGA and ECM is proposed for the inverse design of dual-bandpass metasurface filters.•The expected operating frequency of the proposed metasurface filter is switchable within the X-, Ku-, and K-bands.•The device is insensitive to the polarization and incident angle.
Abstract
In order to maintain electromagnetic silence and avoid external interference, UAV clusters usually use purely azimuthal passive positioning methods to adjust the position of UAVs when ...attempting formation flights. However, due to the large number of UAVs flying in formation, it is difficult to perform effective localization, although they can keep flying at an altitude based on their own sensors. Therefore, this paper establishes a passive positioning model based on the triangulation method under the condition of pure azimuthal passive positioning, solves the coordinates of the UAV position of the received signal by using the least squares problem, and designs the UAV position adjustment scheme by using the optimal scheduling model based on the immune-genetic algorithm, so as to improve the positioning accuracy and survivability of the UAV.