Fast Non-dominated Sorting Genetic Algorithm Research Articles

Long Short-Term Memory Parameter Optimization Based on Improved Sparrow Search Algorithm for Molten Iron Quality Prediction

Blast furnace (BF) ironmaking is a key process in iron and steel production. Because BF ironmaking is a dynamic time series process, it is more appropriate to use a recurrent neural network for modeling. The long short-term memory (LSTM) network is commonly used to model time series data. However, its model performance and generalization ability heavily depend on the parameter configuration. Therefore, it is necessary to study parameter optimization for the LSTM model. The sparrow search algorithm (SSA) holds advantages over traditional optimization algorithms in several aspects, such as no need for prior knowledge, fewer parameters, fast convergence, and high scalability. However, the algorithm still faces some challenges, such as the tendency to become trapped in the local optimum and the imbalance between global search ability and local search ability. Therefore, on the basis of SSA, this study examined the Levy flight strategy, sine search strategy, and step size factor adjustment strategy to improve it. This algorithm, improved by three strategies, is called the improved sparrow search algorithm (ISSA). Then, the ISSA-LSTM model was established. Furthermore, considering the limitations of SSA in dealing with multi-objective problems, the fast non-dominated sorting genetic algorithm (NSGAII) was introduced, and the ISSA-NSGAII model was established. Finally, experimental validation was performed using real blast furnace operation data, which demonstrated the proposed algorithm’s superiority in parameter optimization for the LSTM model and prediction for real industrial data.

Route Optimization for Hazardous Chemicals Transportation under Time-Varying Conditions

Since accidents of hazardous chemicals transportation will cause serious loss to the surrounding environment and lives and properties, this paper studies the transportation route optimization problem of hazardous chemicals under dynamic time-varying conditions. Combined with the goal of green sustainable development, a multiobjective nonlinear optimization model is constructed to minimize the transportation risk, transportation cost, and carbon emissions generated in the transportation. The model is solved by the improved Fast Non-Dominated Sorting Genetic Algorithm with Elite Strategy (NSGA-II) algorithm. The effectiveness of the model and the algorithm are tested on the Sioux Falls network. The experimental results show that under time-varying conditions, a vehicle’s departure at different times will generate different transportation costs and risks. Therefore, enterprises need to rationally arrange the departure time of vehicles according to the time windows of customer nodes and road conditions. In additio, from the relationship between the optimization objectives, in order to achieve green, sustainable and low-risk transportation, enterprises should first reduce their transportation costs.

RGBW LED mixing temperature compensation method with high output consistency

This paper proposes a temperature compensation method for RGBW LED mixing based on fast non-dominated sorting genetic algorithm(NSGA-II). The proposed method can achieve compensation for temperature-induced changes in LED correlated color temperature (CCT), color fidelity (Rf) and color gamut index (Rg) by predicting the spectral power distribution (SPD) at different temperatures. The SPD-temperature model of the RGBW LED light source is established by measuring the spectral power distribution of LEDs at different temperatures. Based on the established model, NSGA-II is used to compensate the mixing temperature of the RGBW LED light source according to the spectral superposition theorem. The experimental results show that the fit of the established temperature-spectral model is R2 > 0.98, and the deviation of the compensated mixing results from the initial state of the light source is less than 10 K in CCT; the deviation value of Rf is less than 4 % in the range of 2000 K-7000 K, and less than 2.15 % in the range of 3000 K-7000 K; and the deviation value of Rg in the range of 2000 K-7000 K is less than 4.46 %.

Application of hybrid intelligent algorithm for multi-objective optimization of high performance concrete in complex alpine environment highway

Concrete mix proportion affects concrete performance and cost. Therefore, it arouses an increase of interest in the research on performance improvements in concrete through the optimization of the raw material mix proportion, especially in the high cold, high-salinity and other complex environment. In this paper, an intelligent multi-objective optimization framework is constructed based on Bayesian optimization Random Forest (BO-RF) algorithm and fast non-dominated sorting genetic algorithm (NSGA-III). The key factors affecting concrete performance are taken as the input indexes, the freezing resistance, impermeability, carbonization depth and cost are taken as the evaluation indexes of concrete. Based on 400 groups of freeze–thaw cycle of salt invasion experiments in cold environment, the orthogonal experiment method is used to obtain the index system of the original data sets, then, the RF prediction algorithm is adopted to establish the key factors and performance index of a nonlinear mapping relationship and the Bayesian optimization random forest is used to establish a high-precision fitness function. Ultimately, the BO-RF-NSGA-III model is applied for multiobjective optimization. The results show that (1) Based on the proposed framework, the rapid prediction and optimization of concrete performance can be realized, which can well meet the needs of the complex alpine environment (2) Accurate model prediction can be made through BO-RF. The R2 values obtained at the time of prediction range from 0.944 to 0.998, the mean absolute error (MAE) range from 0.001 to 0.09. (3) Based on BO-RF-NSGA-III and grey correlation method, the comprehensive optimal mix proportion of concrete is obtained.

Co-optimization of injection parameters and injector layouts for a methanol/diesel direct dual-fuel stratification (DDFS) engine

Direct dual fuel stratification (DDFS) is a promising combustion mode to achieve satisfactory engine performance with the effective control of ignition and combustion processes. In this study, a DDFS engine fueled with methanol and diesel was investigated at low loads based on a four-stroke light-duty naturally aspirated engine. Both injection parameters and injector layouts of the two fuels were co-optimized by the fast nondominated sorting genetic algorithm (NSGA-II). The results show that the fractions, injection timings, spray half-included angles, and injector positions of the two fuels all showed significant influences on engine performance. Finally, the high methanol fraction, advanced diesel injection timing, methanol injection timing near the top dead center, and large spray half-included angle of methanol were adopted in the optimal case to achieve both low EISFC and NOx simultaneously. Meanwhile, a centrally-mounted methanol injector was beneficial to shorten combustion duration, and the diesel injector can be arranged in a semicircle area with a radius of approximately 1.14 cm to provide the sufficiently high temperature for the complete combustion of methanol.

Solving the Vehicle Routing Problem for a Reverse Logistics Hybrid Fleet Considering Real-Time Road Conditions

In this study, a bi-objective optimization model was established to solve the cooperative distribution problem of a multi-center hybrid fleet by integrating reverse logistics under real-time road conditions. According to the characteristics of the problem and considering the power level and battery capacity of electric vehicles, the multi-objective immune genetic algorithm (MOIGA) was designed and compared with an elitist strategy genetic algorithm, i.e., the fast non-dominated sorting genetic algorithm (NSGA-II). The scale of the MOIGA solution set exceeded that of the NSGA-II, which proved that the global search ability of MOIGA was better than that of the NSGA-II. The operating efficiency of the MOIGA was lower than that of the NSGA-II, but it could also find the optimal solution within an acceptable time range. This method can reduce the total cost of operating a hybrid fleet and can meet the needs of customers, and therefore, improve customer satisfaction.

Precision agriculture management based on a surrogate model assisted multiobjective algorithmic framework

Sustainable intensification needs to optimize irrigation and fertilization strategies while increasing crop yield. To enable more precision and effective agricultural management, a bi-level screening and bi-level optimization framework is proposed. Irrigation and fertilization dates are obtained by upper-level screening and upper-level optimization. Subsequently, due to the complexity of the problem, the lower-level optimization uses a data-driven evolutionary algorithm, which combines the fast non-dominated sorting genetic algorithm (NSGA-II), surrogate-assisted model of radial basis function and Decision Support System for Agrotechnology Transfer to handle the expensive objective problem and produce a set of optimal solutions representing a trade-off between conflicting objectives. Then, the lower-level screening quickly finds better irrigation and fertilization strategies among thousands of solutions. Finally, the experiment produces a better irrigation and fertilization strategy, with water consumption reduced by 44%, nitrogen application reduced by 37%, and economic benefits increased by 7 to 8%.

Multi-objective optimization of proton exchange membrane fuel cell geometry and operating parameters based on three new performance evaluation indexes

Key issues such as performance, durability, and cost limit the large-scale commercial application of the proton exchange membrane fuel cell (PEMFC). The distribution of reactants in the PEMFC is not uniform, which will make the distribution of current density uneven, and then affect its durability. Different from the output power of the PEMFC as the performance evaluation index, the flow uniformity of the reactants, diffusion flux, and ohmic resistance are proposed as the comprehensive performance evaluation index. Firstly, the physical model of three-dimensional two-phase non– isothermal PEMFC was established. Secondly, six parameters were selected and the first-order finite-difference sensitivity of each parameter of the flow uniformity of the reactants and the diffusion flux was calculated. Five parameters were selected as optimization objects through sensitivity analysis. Then, the five parameters were scanned and parameterized, and the obtained data were used to train the neural network as a surrogate model. Finally, based on the fast non-dominated sorting genetic algorithm with elite strategy (NSGA-II), three PEMFC performance indexes including the flow uniformity of the reactants, the diffusion flux, and the ohmic resistance were optimized simultaneously. In this study, from Pareto solutions obtained by multi-objective optimization, the point with the largest diffusion flux is selected as the optimal solution, that is, the flow uniformity of reactants is 0.458411026, the diffusion flux is 0.049903274, and the ohmic resistance is 0.047476574. The optimized model has a higher polarization curve, which means better fuel cell performance. The flow uniformity of the reactants determines that the current density of the optimized model is more uniform than that of the basic model, which makes the fuel cell have better durability. Therefore, the fuel cell performance optimization method proposed in this paper is feasible. The three new performance evaluation indexes can provide a reference for the study of fuel cell performance and durability in the future.

A Variable-Order Fuzzy Logic Controller Design Method for an Unmanned Underwater Vehicle Based on NSGA-II

UUV depth control requires the controlled system to have good transient response and robustness under the premise of ensuring real-time performance. The flexibility of fractional-order control provides an idea to solve this problem. This paper proposes a controller design method for UUV depth control (VD-SIFLC) based on fractional calculus, fuzzy control, dynamic parameters and a fast non-dominated sorting genetic algorithm (NSGA-II). First, the overall structure of the controller, the UUV model and the model of external disturbances are presented. Then, the design methods of control input, order selector, membership function and scale factor selector are given, respectively. Then, the necessary conditions, such as optimization objectives and optimization parameters in the optimization algorithm, are analyzed. Finally, the effectiveness of the proposed control scheme is verified by comparative experiments with the SIFLC. Simulation results show that the controlled system with the VD-FIFLC could achieve better robustness and dynamic and steady-state performance. Moreover, according to the actual task requirements, the appropriate parameters can be selected by the user from the pareto solution set, which is suitable to be used in the actual applications.

The Analysis of Environmental Cost Control of Manufacturing Enterprises Using Deep Learning Optimization Algorithm and Internet of Things

Under the background of the Internet of things (IoT), the problems between the actual production and the environment are also prominent. The environmental cost control in the production process of manufacturing enterprises are discussed to reduce the environmental cost and promote the improvement of production efficiency. First, the environmental cost under the background of IoT is analyzed. Also, the environmental cost control methods in the production process of traditional manufacturing enterprises are investigated. Second, based on the principle of traditional genetic algorithm, the fast-nondominated sorting genetic algorithm (NSGA-II) of multiobjective genetic algorithm is introduced to complete the optimization of BP neural network (BPNN) algorithm in deep learning (DL), and the multiobjective GA optimization BPNN model is established. Finally, the multiobjective GA algorithm is used to empirically analyze the environmental cost control capability of a paper-making enterprise. It is compared with enterprises with excellent and poor environmental cost control capabilities in the same industry to find out secondary indexes. The results show that environmental costs have long-term and economic characteristics. The global search ability of BPNN optimized by multiobjective GA is improved, and the local optimal dilemma is avoided. Through empirical analysis, it is found that the comprehensive capability of the environmental cost control of the enterprise is better, scored 79 or more, and the indexes of insufficient development and advantages are obtained. As IoT rapidly develops, it is necessary to further improve the ability of enterprises in environmental cost management, which is very important to promote the development of enterprises and enhance their core competitiveness. It is hoped that this investigation can provide certain reference significance for improving the environmental cost management capability of enterprises, increasing production efficiency, and reducing environmental costs.

An Efficient Computing Offloading Scheme Based on Privacy-Preserving in Mobile Edge Computing Networks

Computation offloading is an important technology to achieve lower delay communication and improve the experience of service (EoS) in mobile edge computing (MEC). Due to the openness of wireless links and the limitation of computing resources in mobile computing process, the privacy of users is easy to leak, and the completion time of tasks is difficult to guarantee. In this paper, we propose an efficient computing offloading algorithm based on privacy-preserving (ECOAP), which solves the privacy problem of offloading users through the encryption technology. To avoid the algorithm falling into local optimum and reduce the offloading user energy consumption and task completion delay in the case of encryption, we use the improved fast nondominated sorting genetic algorithm (INSGA-II) to obtain the optimal offloading strategy set. We obtain the optimal offloading strategy by using the methods of min-max normalization and simple additive weighting based on the optimal offloading strategy set. The ECOAP algorithm can preserve user privacy and reduce task completion time and user energy consumption effectively by comparing with other algorithms.

Neural network joint capacity-power control strategy based on NSGAII-BP for interference suppression in LEO satellite uplinks

Due to the long distance between satellites and the earth, uplink users need considerable energy to achieve satellite communication. Therefore, the energy efficiency is very important for user terminals. In addition, multibeam Low Earth Orbit (LEO) satellite networks may cause cochannel interference between beams because of full frequency reuse. Moreover, power competition among users will easily occur if the users begin to privately increase the transmission power. Power competition limits capacity and reduces energy efficiency. To solve these problems, this paper proposes a power control strategy balancing capacity and energy efficiency. A dual-objective optimization model is established based on the maximum transmission power constraint and the minimum signal-to-interference ratio (SIR) constraint. The model is solved by a back propagation (BP) neural network based on the fast nondominated sorting genetic algorithm (NSGAII). The neural network can adjust the optimization degree of the energy efficiency and capacity by preference factors. The simulation experiment results show that, while the user minimum transmission rate increases, the EE optimization of the NSGAII-BP neural network is better than that of the traditional weighting method.

A Two-Level Integrated Scheduling Strategy for Vehicle-Network Synergy considering New Energy Consumption

With the substantial increase in the number of electric vehicles, the charging of electric vehicles without regulation and scale control will bring about problems, such as overloading of distribution transformers; the proportion of new energy power generation is also increasing year by year, and the access of new energy to the power grid will cause volatility. In order to solve the problems above, this paper proposed a coordinated and orderly scheduling strategy considering new energy consumption, which protects the interests of both users and the integrated power grid. First, a two-level vehicle-network interaction model considering both supply and demand sides was established. The upper-level model optimized the indicators on the distribution grid side, and a term of charge-discharge margin as well as grid-side load variance model was proposed. The lower-level optimization model was set based on the users’ condition. The average discharge rate index was defined to evaluate the battery loss satisfaction in the scheduling strategy, which fully considered users’ charging and discharging cost, and finally achieved a win-win situation between the power grid and the user. Secondly, the fast nondominated sorting genetic algorithm (NSGA-II) was used to figure out the effect of the strategy proposed in this paper, and a community is taken as an example for simulation. The results confirmed the economy and rationality of the above strategy, by rationally scheduling the charging and discharging behavior of electric vehicles, consuming new energy, restraining the fluctuation of the remaining new energy power generation, realizing the dynamic balance between the charging and discharging load and the output of new energy in a certain area, and finally effectively suppressing the fluctuation of the power grid load while improving the availability of clean energy.

Malware detection based on multi‐objective convolution restricted Boltzmann machine model and constraint‐dividing crossover strategy algorithm

AbstractMalicious code, which is used to threaten network security, has been improved by many methods and strategies. However, the use of unreasonable deep learning models and single‐objective algorithms often affects the accuracy of data classification. Moreover, as an optimization problem, the existence of low‐quality datasets (imbalanced datasets) constrains the training effect of neural network models. Therefore, it is a big challenge to effectively design data processing methods and suitable training models. To enhance the robustness of the model and obtain better data classification results, it is essential to develop an efficient training model and strategy. To resolve this problem, a novel multi‐objective convolution restricted Boltzmann machine (CRBM) model based on the spatial pyramid pooling strategy is proposed to identify images and classify data in this study. Moreover, a fast nondominated sorting genetic algorithm based on the constraint‐dividing crossover strategy (CDCS‐NSGA‐II) is designed to optimize the imbalance datasets of the malware families. Extensive experimental results show that the multi‐objective CRBM model designed in this study combined with the CDCS‐NSGA‐II algorithm can effectively enhance the learning ability of the dataset, increase the effect of data classification and improve the robustness of the model.

A three-tier programming model for service composition and optimal selection in cloud manufacturing

The process of service composition and optimal selection in cloud manufacturing (CMfg-SCOS) involves three types of users: service demanders, resource providers, and cloud platform operators. The interests of all users are a research focus of CMfg-SCOS, as their participation in the CMfg system directly affects the efficiency and long-term development of CMfg. However, the current research on CMfg-SCOS rarely considers the interests of all three types of users simultaneously, and the interest of resource providers is not clearly defined, which lags behind the reality of CMfg. Therefore, this study first proposes a three-tier programming model of CMfg-SCOS that considers the interests of service demanders, cloud platform operators, and resource providers. At the lower level of the model, service demanders are the decision makers, aiming to minimize time and cost and maximize service quality. At the middle level of the model, cloud platform operators are the decision makers, aiming to maximize resource use and flexibility in the face of uncertain environments. At the upper level, resource providers are the decision makers, aiming to maximize enterprise surplus. Then, this study develops an improved fast nondominated sorting genetic algorithm with advancement and inheritance (namely, a-i-NSGA-II) to solve the three-tier model efficiently. Numerical experiments conducted in this study found that in comparison to the art of state algorithms, including original nondominated sorting genetic algorithm II (NSGA-II), multiobjective particle swarm optimization (MOPSO), and multiobjective spotted hyena optimizer (MOSHO), the proposed a-i-NSGA-II has better diversity and comprehensive performance at the middle level of the model and better solution quality at the upper level. Furthermore, a case study of the actual production of an automobile fuel tank assembly enterprise verifies the effectiveness of the proposed model and algorithm.

Optimization of the transmission characteristics of an HMCVT for a high-powered tractor based on an improved NSGA-II algorithm

The hydro-mechanical continuously variable transmission (HMCVT) is a critical component of the power transmission system in a tractor. However, the complexity of the operating conditions imposes high requirements on the transmission characteristics. To improve the powerful performance and economy of HMCVTs and satisfy the operational demands of high-powered tractors, a new optimization design method for the characteristic parameters of an HMCVT is proposed. First, the characteristics of an HMCVT are modeled, and the influence of the structural parameters on the transmission characteristics is analyzed. Then, HMCVT performance evaluation indexes are formulated. In accordance with the speed regulation of system, power performance, and economy characteristics, a multi-objective optimization mathematical model is established, and an improved fast non-dominated sorting genetic algorithm (INSGA-II) is designed. The introduction of a normal distribution crossover operator (NDX) and an improved adaptive adjustment mutation operator not only ensures the population diversity but also improves the Pareto solution convergence properties during the process of genetic evolution. The superiority of INSGA-II is verified by comparison with a traditional multi-objective genetic algorithm. Finally, the optimization results show that the torque ratio is increased by approximately 2.81%, 14.32%, 2.31%, and 15.07% in HM1, HM2, HM3, and HM4 respectively. The transmission efficiency is increased by approximately 3.48% and 1.97% in HM1 (HM3) and HM2 (HM4). Also, INSGA-II finds the optimal solution with a faster speed and shorter optimization time than MULGA. This research can serve as a reference for the design and optimization of HMCVTs for high-powered tractors.

Trends summarization of times series: a multi-objective genetic algorithm-based model

Aim: The explosion of the amounts of data generated in many application domains, makes the paradigm of data summarization more essential. Furthermore, it is of a great interest to effectively handle some specific needs. In this work, we discuss an advanced model to drive linguistic summarization in the context of time series. This model relies on a multi-objective genetic algorithm mechanism to generate a set of best summaries from a large number of candidates. Methods: To achieve this objective, the current work is divided into two parts: The first part is dedicated for extracting the linguistic summaries of the dynamic characteristics of the trends of time series. It is achieved using the traditional genetic algorithm where the fitness function represents the truth degree of the linguistic quantified proposition. The second part is devoted to formalise the problem of interest as a multi-criteria optimization problem. We use different quality measures of summary as targets for improving the predicted set of summaries. To reach this goal, we use the Fast Non-Dominated Sorting Genetic Algorithm NSGA-II. Results: We evaluate the proposed approach on real data from a Smart Campus application (Neocampus project of the University of Toulouse, France). The results are promising and confirming the usability of the proposed approach. Conclusion: The proposed approach overcomes the problem of the overabundance of irrelevant linguistic summaries of the time series. It allows selecting a set of best summaries regarding some relevant criteria.

Multi-Objective Optimization of Ocean Thermal Energy Conversion System Based on Fast Non-Dominated Sorting Genetic Algorithm

Multi-Objective Optimization of Ocean Thermal Energy Conversion System Based on Fast Non-Dominated Sorting Genetic Algorithm

An enhanced fast non-dominated solution sorting genetic algorithm for multi-objective problems

Multi-modal multi-objective optimization problem (MMOPs) has attracted more and more attention in evolutionary computing recently. It is not easy to solve these problems using the existing evolutionary algorithms. The non-dominated solution sorting genetic algorithm (NSGA-II) has poor PS distribution and convergence. In this paper, an enhanced fast NSGA-II based on a special congestion strategy and adaptive crossover strategy, namely ASDNSGA-II is proposed. In the ASDNSGA-II, the strategy with a special congestion degree is used to improve the selection strategy. Then a new adaptive crossover strategy is designed by evaluating the advantages and disadvantages of the SBX crossover strategy with the ability to solve high dimensions and the BLX-α with the ability of Pareto solution to produce offspring solutions. These can ensure the generation of offspring solutions around individuals with large crowding degrees and balance the convergence and diversity of decision space and object space. It can improve PS distribution and convergence and maintain PF precision. Eight functions of MMF1-MMF8 from the CEC2020 are selected to prove the effectiveness of the ASDNSGA-II. By comparing several latest multi-modal multi-objective evolutionary algorithms, the results show that the ASDNSGA-II can effectively find the global Pareto solution set and improve the distribution and convergence of PS.

Variable selection for near-infrared spectrum modeling based on fast nondominated sorting genetic algorithm

Building an excellent model is crucial for the near-infrared technology used in various fields. Full-spectrum model building has negative influence on the predictive ability of models owing to the use of several invalid variables, variable selection can improve model performance. Several variable selection approaches along with evolutionary and swarm intelligent algorithms have been successfully implemented. However, most approaches lack relevance between the near-infrared spectral features and analyte, thus increasing the risk of model overfitting. In this study, a spectral variable selection approach based on a fast nondominated sorting genetic algorithm is proposed for improving the relevance between the near-infrared spectral features and analyte. This approach includes two objective functions: (1) maximizing the ratio of interclass to in-class sum of standard deviation and (2) minimizing the sum of correlation coefficient between the selected variables. The former focuses on the relevance between the spectral features and analyte, whereas the latter focuses on reducing the correlation between the selected variables to avoid invalid variables. The fast nondominated sorting genetic algorithm has multiple solutions, such as Pareto solution set, and the optimal solution is determined using the root mean square error of cross validation. To validate this algorithm using partial least squares, tobacco nicotine and total sugar models were built under varying number of selected variables. In comparison to a model with 1036 variables, the root mean square error of prediction of the nicotine model with 150–600 variables decreased by more than 15% and up to 23.93%, and that of the total sugar model with 100–600 variables decreased by more than 7.5% and up to 13.79%. This study showed that model performance can be significantly improved under a wide range of variables selected by the fast nondominated sorting genetic algorithm. Additionally, better prediction was obtained by fast nondominated sorting genetic algorithm when compared to interval selectivity ratio and full spectrum partial least squares modeling.