Multi-Objective Optimization with Artificial Neural Network Based Robust Paddy Yield Prediction Model

Agriculture plays a vital role in the food production process that occupies nearly one-third of the total surface of the earth.Rice is propagated from the seeds of paddy and it is a stable food almost used byfifty percent of the total world population.The extensive growth of the human population alarms us to ensure food security and the country should take proper food steps to improve the yield of food grains.This paper concentrates on improving the yield of paddy by predicting the factors that influence the growth of paddy with the help of Evolutionary Computation Techniques.Most of the researchers used to relay on historical records of meteorological parameters to predict the yield of paddy.There is a lack in analyzing the day to day impact of meteorological parameters such as direction of wind,relative humidity,Instant Wind Speed in paddy cultivation.The real time meteorological data collected and analysis the impact of weather parameters from the day of paddy sowing to till the last day of paddy harvesting with regular time series.A Robust Optimized Artificial Neural Network(ROANN)Algorithm with Genetic Algorithm(GA)and Multi Objective Particle Swarm Optimization Algorithm(MOPSO)proposed to predict the factors that to be concentrated by farmers to improve the paddy yield in cultivation.A real time paddy data collected from farmers of Tamilnadu and the meteorological parameters were matched with the cropping pattern of the farmers to construct the database.The input parameters were optimized either by using GA or MOPSO optimization algorithms to reconstruct the database.Reconstructed database optimized by using Artificial Neural Network Back Propagation Algorithm.The reason for improving the growth of paddy was identified using the output of the Neural Network.Performance metrics such as Accuracy,Error Rate etc were used to measure the performance of the proposed algorithm.Comparative analysis made between ANN with GA and ANN with MOPSO to identify the recommendations for improving the paddy yield.

B^(2)C^(3)NetF^(2):Breast cancer classification using an end‐to‐end deep learning feature fusion and satin bowerbird optimization controlled Newton Raphson feature selection

Currently,the improvement in AI is mainly related to deep learning techniques that are employed for the classification,identification,and quantification of patterns in clinical images.The deep learning models show more remarkable performance than the traditional methods for medical image processing tasks,such as skin cancer,colorectal cancer,brain tumour,cardiac disease,Breast cancer(BrC),and a few more.The manual diagnosis of medical issues always requires an expert and is also expensive.Therefore,developing some computer diagnosis techniques based on deep learning is essential.Breast cancer is the most frequently diagnosed cancer in females with a rapidly growing percentage.It is estimated that patients with BrC will rise to 70%in the next 20 years.If diagnosed at a later stage,the survival rate of patients with BrC is shallow.Hence,early detection is essential,increasing the survival rate to 50%.A new framework for BrC classification is presented that utilises deep learning and feature optimization.The significant steps of the presented framework include(i)hybrid contrast enhancement of acquired images,(ii)data augmentation to facilitate better learning of the Convolutional Neural Network(CNN)model,(iii)a pre‐trained ResNet‐101 model is utilised and modified according to selected dataset classes,(iv)deep transfer learning based model training for feature extraction,(v)the fusion of features using the proposed highly corrected function‐controlled canonical correlation analysis approach,and(vi)optimal feature selection using the modified Satin Bowerbird Optimization controlled Newton Raphson algorithm that finally classified using 10 machine learning classifiers.The experiments of the proposed framework have been carried out using the most critical and publicly available dataset,such as CBISDDSM,and obtained the best accuracy of 94.5%along with improved computation time.The comparison depicts that the presented method surpasses the current state‐ofthe‐art approaches.

Optimization of CNC Turning Machining Parameters Based on Bp-DWMOPSO Algorithm

Cutting parameters have a significant impact on the machining effect.In order to reduce the machining time and improve the machining quality,this paper proposes an optimization algorithm based on Bp neural networkImproved Multi-Objective Particle Swarm(Bp-DWMOPSO).Firstly,this paper analyzes the existing problems in the traditional multi-objective particle swarm algorithm.Secondly,the Bp neural network model and the dynamic weight multi-objective particle swarm algorithm model are established.Finally,the Bp-DWMOPSO algorithm is designed based on the established models.In order to verify the effectiveness of the algorithm,this paper obtains the required data through equal probability orthogonal experiments on a typical Computer Numerical Control(CNC)turning machining case and uses the Bp-DWMOPSO algorithm for optimization.The experimental results show that the Cutting speed is 69.4 mm/min,the Feed speed is 0.05 mm/r,and the Depth of cut is 0.5 mm.The results show that the Bp-DWMOPSO algorithm can find the cutting parameters with a higher material removal rate and lower spindle load while ensuring the machining quality.This method provides a new idea for the optimization of turning machining parameters.

Noise Reduction of an Axial Piston Pump by Valve Plate Optimization

Current researches mainly focus on the investigations of the valve plate utilizing pressure relief grooves. However,air?release and cavitation can occur near the grooves. The valve plate utilizing damping holes show excellent perfor?mance in avoiding air?release and cavitation. This study aims to reduce the noise emitted from an axial piston pump using a novel valve plate utilizing damping holes. A dynamic pump model is developed,in which the fluid properties are carefully modeled to capture the phenomena of air release and cavitation. The causes of di erent noise sources are investigated using the model. A comprehensive parametric analysis is conducted to enhance the understanding of the e ects of the valve plate parameters on the noise sources. A multi?objective genetic algorithm optimization method is proposed to optimize the parameters of valve plate. The amplitudes of the swash plate moment and flow rates in the inlet and outlet ports are defined as the objective functions. The pressure overshoot and undershoot in the piston chamber are limited by properly constraining the highest and lowest pressure values. A comparison of the various noise sources between the original and optimized designs over a wide range of pressure levels shows that the noise sources are reduced at high pressures. The results of the sound pressure level measurements show that the optimized valve plate reduces the noise level by 1.6 d B(A) at the rated working condition. The proposed method is e ective in reducing the noise of axial piston pumps and contributes to the development of quieter axial piston machines.

Optimization approach hydroforming car beam billets based grey system theory

Perfect combination of structural size parameters of the hydroforming billets is essential to obtain even wall thicknesses of the car beam. Finite element （ FE ） analysis on hydroforming car beam was carried out, and the results were optimized according to multiple quality objectives by the grey system theory. With bending angle, bending radius and hight difference along the axis direction as variables, orthogonal FE analyses were conducted and the minimum and maximum wall thicknes ses of the billets with different sizes were obtained. Taking the minimum and maximum wall thick nesses as two references, the correlation coefficient between the data for reference and those for comparison by the grey system theory reduced multi objectives to a single quality objective, and the average correlation level of every billet facilitated the optimization of size parameters for hydroform ing car beam. The trial production showed that the optimization approach satisfied the need of hy droforming car beams.

Multi-objective route planning approach for timely searching tasks of a supervised robot

To performance efficient searching for an operator-supervised mobile robot, a multiple objectives route planning approach is proposed considering timeliness and path cost. An improved fitness function for route planning is proposed based on the multi-objective genetic algorithm （MOGA） for multiple objectives traveling salesman problem （MOTSP）. Then, the path between two route nodes is generated based on the heuristic path planning method A ＊. A simplified timeliness function for route nodes is proposed to represent the timeliness of each node. Based on the proposed timeliness function, experiments are conducted using the proposed two-stage planning method. The experimental results show that the proposed MOGA with improved fitness function can perform the searching function well when the timeliness of the searching task needs to be taken into consideration.

GPPre:A Python⁃Based Tool in Grasshopper for Office Building Performance Optimization

With the development of the economic and low⁃carbon society,high⁃performance building(HPB)design plays an increasingly important role in the architectural area.The performance of buildings usually includes the building energy consumption,building interior natural daylighting,building surface solar radiation,and so on.Building performance simulation(BPS)and multiple objective optimizations(MOO)are becoming the main methods for obtaining a high performance building in the design process.Correspondingly,the BPS and MOO are based on the parametric tools,like Grasshopper and Dynamo.However,these tools are lacking the data analysis module for designers to select the high⁃performance building more conveniently.This paper proposes a toolkit“GPPre”developed based on the Grasshopper platform and Python language.At the end of this paper,a case study was conducted to verify the function of GPPre,which shows that the combination of the sensitivity analysis(SA)and MOO module in the GPPre could aid architects to design the buildings with better performance.

Breeding Particle Swarm Optimization for Railways Rolling Stock Preventive Maintenance Scheduling

The goal of railway rolling stock maintenance and replacement approaches is to reduce overall cost while increasing reliability which is multi objective optimization problem and a proper predictive maintenance scheduling table should be adequately designed. We propose Breeding Particle Swarm Optimization (BPSO) model based on the concepts of Breeding Swarm and Genetic Algorithm (GA) operators to design this table. The practical experiment shows that our model reduces cost while increasing reliability compared to other models previously utilized.

Research on Comprehensive Control of Power Quality of Port Distribution Network Considering Large-Scale Access of Shore Power Load

In view of the problem of power quality degradation of port distribution network after the large-scale application of shore power load,a method of power quality management of port distribution network is proposed.Based on the objective function of the best power quality management effect and the smallest investment cost of the management device,the optimization model of power quality management in the distribution network after the large-scale application of large-capacity shore power is constructed.Based on the balance between the economic demand of distribution network resources optimization and power quality management capability,the power quality of distribution network is considered comprehensively.The proposed optimization algorithm for power quality management based on Matlab and OpenDSS is proposed and analyzed for port distribution networks.The simulation results show that the proposed optimizationmethod can maximize the power qualitymanagement capability of the port distribution network,and the proposed optimization algorithm has good convergence and global optimization finding capability.

Fixed-Time Cluster Consensus for Multi-Agent Systems with Objective Optimization on Directed Networks

This paper studies the cluster consensus of multi-agent systems(MASs)with objective optimization on directed and detail balanced networks,in which the global optimization objective function is a linear combination of local objective functions of all agents.Firstly,a directed and detail balanced network is constructed that depends on the weights of the global objective function,and two kinds of novel continuous-time optimization algorithms are proposed based on time-invariant and timevarying objective functions.Secondly,by using fixed-time stability theory and convex optimization theory,some sufficient conditions are obtained to ensure that all agents'states reach cluster consensus within a fixed-time,and asymptotically converge to the optimal solution of the global objective function.Finally,two examples are presented to show the efficacy of the theoretical results.

Optimization methods for regularization-based ill-posed problems： a survey and a multi-objective framework

Ill-posed problems are widely existed in signat processing. In this paper, we review popular regularization models such as truncated singular value decomposi- tion regularization, iterative regularization, variational regularizafion. Meanwhile, we also retrospect popular optimiza- tion approaches and regularization parameter choice meth- ods. In fact, the regularization problem is inherently a multi- objective problem. The traditional methods usually combine the fidelity term and the regularization term into a single- objective with regularization parameters, which are difficult to tune. Therefore, we propose a multi-objective framework for ill-posed problems, which can handle complex features of problem such as non-convexity, discontinuity. In this framework, the fidelity term and regularization term are optimized simultaneously to gain more insights into the ill-posed prob- lems. A case study on signal recovery shows the effectiveness of the multi-objective framework for ill-posed problems.

Cleaner production for continuous digester processes based on hybrid Pareto genetic algorithm

Pulping production process produces a large amount of wastewater and pollutant emitted, which has become one of the main pollution sources in pulp and paper industry. To solve this problem, it is necessary to implement cleaner production by using modeling and optimization technology. This paper studies the modeling and multi\|objective genetic algorithms for continuous digester process. First, model is established, in which environmental pollution and saving energy factors are considered. Then hybrid genetic algorithm based on Pareto stratum\|niche count is designed for finding near\|Pareto or Pareto optimal solutions in the problem and a new genetic evaluation and selection mechanism is proposed. Finally using the real data from a pulp mill shows the results of computer simulation. Through comparing with the practical curve of digester,this method can reduce the pollutant effectively and increase the profit while keeping the pulp quality unchanged.

Influence of yaw damper layouts on locomotive lateral dynamics performance:Pareto optimization and parameter analysis

High-speed locomotives are prone to carbody or bogie hunting when the wheel-rail contact conicity is excessively low or high.This can cause negative impacts on vehicle dynamics performance.This study presents four types of typical yaw damper layouts for a high-speed locomotive(Bo-Bo)and compares,by using the multi-objective optimization method,the influences of those layouts on the lateral dynamics performance of the locomotive;the linear stability indexes under lowconicity and high-conicity conditions are selected as optimization objectives.Furthermore,the radial basis function-based highdimensional model representation(RBF-HDMR)method is used to conduct a global sensitivity analysis(GSA)between key suspension parameters and the lateral dynamics performance of the locomotive,including the lateral ride comfort on straight tracks under the low-conicity condition,and also the operational safety on curved tracks.It is concluded that the layout of yaw dampers has a considerable impact on low-conicity stability and lateral ride comfort but has little influence on curving performance.There is also an important finding that only when the locomotive adopts the layout with opening outward,the difference in lateral ride comfort between the front and rear ends of the carbody can be eliminated by adjusting the lateral installation angle of the yaw dampers.Finally,force analysis and modal analysis methods are adopted to explain the influence mechanism of yaw damper layouts on the lateral stability and differences in lateral ride comfort between the front and rear ends of the carbody.

Application of Grade Algorithm Based Approach along with PV Analysis for Enhancement of Power System Performance

This paper presents an application of GRADE Algorithm based approach along with PV analysis to solve multi objective optimization problem of minimizing real power losses, improving the voltage profile and hence enhancing the performance of power system. GRADE Algorithm is a hybrid technique combining genetic and differential evolution algorithms. Control variables considered are Generator bus voltages, MVAR at capacitor banks, transformer tap settings and reactive power generation at generator buses. The optimal values of the control variables are obtained by solving the multi objective optimization problem using GRADE Algorithm programmed using M coding in MATLAB platform. With the optimal setting for the control variables, Newton Raphson based power flow is performed for two test systems, viz, IEEE 30 bus system and IEEE 57 bus system for three loading conditions. Minimization of Real power loss and improvement of voltage profile obtained are compared with the results obtained using firefly and particle swarm optimization (PSO) techniques. Improvement of Loadability margin is established through PV curve plotted using continuation power flow with the real power load at the most affected bus as the bifurcation parameter. The simulated output shows improved results when compared to that of firefly and PSO techniques, in term of convergence time, reduction of real power loss, improvement of voltage profile and enhancement of loadability margin.

A Dynamic Programming Approach to the Design of Composite Aircraft Wings

A light and reliable aircraft has been the major goal of aircraft designers. It is imperative to design the aircraft wing skins as efficiently as possible since the wing skins comprise more than fifty percent of the structural weight of the aircraft wing. The aircraft wing skin consists of many different types of material and thickness configurations at various locations. Selecting a thickness for each location is perhaps the most significant design task. In this paper, we formulate discrete mathematical programming models to determine the optimal thicknesses for three different criteria: maximize reliability, minimize weight, and achieve a trade-off between maximizing reliability and minimizing weight. These three model formulations are generalized discrete resource-allocation problems, which lend themselves well to the dynamic programming approach. Consequently, we use the dynamic programming method to solve these model formulations. To illustrate our approach, an example is solved in which dynamic programming yields a minimum weight design as well as a trade-off curve for weight versus reliability for an aircraft wing with thirty locations (or panels) and fourteen thickness choices for each location.

System reliability-based robust design of deep foundation pit considering multiple failure modes

Recently,reliability-based design is a universal method to quantify negative influence of uncertainty in geotechnical engineering.However,for deep foundation pit,evaluating the system safety of retaining structures and finding cost-effective design points are main challenges.To address this,this study proposes a novel system reliability-based robust design method for retaining system of deep foundation pit and illustrated this method via a simplified case history in Suzhou,China.The proposed method included two parts:system reliability model and robust design method.Back Propagation Neural Network(BPNN)is used to fit limit state functions and conduct efficient reliability analysis.The common source random variable(CSRV)model are used to evaluate correlation between failure modes and determine the system reliability.Furthermore,based on the system reliability model,a robust design method is developed.This method aims to find cost-effective design points.To solve this problem,the third generation non-dominated genetic algorithm(NSGA-III)is adopted.The efficiency and accuracy of whole computations are improved by involving BPNN models and NSGA-III algorithm.The proposed method has a good performance in locating the balanced design point between safety and construction cost.Moreover,the proposed method can provide design points with reasonable stiffness distribution.

Optimization Evaluation Test of Strength and Toughness Parameters for Hot-Stamped High Strength Steels

Use of hot-stamped high strength steels （HSHSS） not only reduces the vehicle weight, but also improves the crash safety, therefore more and more mentioned steels are used to produce automobile parts. However, there are several problems especially the low ductility and toughness, which have restricted the application of HSHSS in automobile body. Suitable process parameters are very crucial to improve strength and toughness. In order to study the effect of austenization temperature, soaking time and start deformation temperature on strength and toughness of boron steel 22MnB5, an L9 （34） orthogonal experiment which was analyzed by means of comprehensive evaluation was carried out based on Kahn tear method to obtain the value of fracture toughness. The results indicate that the ex- cellent formability, high strength and toughness of boron steel 22MnB5 with 1.6 mm in thickness are obtained when the austenization temperature is in the range of 920- 950 ℃, the soaking time is 1 min and the start deformation temperature is in the range of 650- 700 ℃. The optimal parameters were used for typical hot stamping structural parts tests. Properties of samples such as tear strength, unit initiation energy and ratio of strength to toughness （RST） were improved by 10.91%, 20.32% and 22.17%, respectively. Toughness was increased substantially on the basis of a small decrease of strength.

A multi-dimensional robust optimization approach for cold-chain emergency medical materials dispatch under COVID-19: A case study of Hubei Province

For the optimization problem of the cold-chain emergency materials(CEM) distribution routes with multi-demand centers and soft time windows and to solve dispatching materials to medical treatment institutions in various places of the disaster areas under COVID-19, a multi-dimensional robust optimization(MRO) model was proposed, which was solved by a hybrid algorithm combined Pareto genetic algorithm and the improved grey relative analysis(IGRA). The proposed model comprehensively takes into consideration of the cost factors of the cold-chain logistics and robustness of solution with the purpose of minimizing the costs and maximizing robustness. The availability of the proposed approach and hybrid algorithm were thoroughly discussed and qualified through a real-world numerical simulation test case, which was a previous risk area located at Hubei Province. Research results show an average-cost reduction of 4.51% and a robustness increment of 11.69% in addition to consider the urgencies of demand. Consequently, not only the costs can be slightly reduced and the robustness be heightened, but also the blindness of the distribution can be avoided effectively with the demand urgency being considered. Research result indicates that when combining with the specific process of supplies dispatching in the prevention and control, the proposed approach is in a far better agreement in practice, and it could meet the diverse requirements of the emergency scenarios flexibly.

Multi-objective Firefly Algorithm for Test Data Generation with Surrogate Model

To solve the emerging complex optimization problems, multi objectiveoptimization algorithms are needed. By introducing the surrogate model forapproximate fitness calculation, the multi objective firefly algorithm with surrogatemodel (MOFA-SM) is proposed in this paper. Firstly, the population wasinitialized according to the chaotic mapping. Secondly, the external archive wasconstructed based on the preference sorting, with the lightweight clustering pruningstrategy. In the process of evolution, the elite solutions selected from archivewere used to guide the movement to search optimal solutions. Simulation resultsshow that the proposed algorithm can achieve better performance in terms ofconvergence iteration and stability.

A cluster positioning architecture and relative positioning algorithm based on pigeon fock bionics

Unmanned clusters can realize collaborative work,fexible confguration,and efcient operation,which has become an important development trend of unmanned platforms.Cluster positioning is important for ensuring the normal operation of unmanned clusters.The existing solutions have some problems such as requiring external system assistance,high system complexity,poor architecture scalability,and accumulation of positioning errors over time.Without the aid of the information outside the cluster,we plan to construct the relative position relationship with north alignment to adopt formation control and achieve robust cluster relative positioning.Based on the idea of bionics,this paper proposes a cluster robust hierarchical positioning architecture by analyzing the autonomous behavior of pigeon focks.We divide the clusters into follower clusters,core clusters,and leader nodes,which can realize fexible networking and cluster expansion.Aiming at the core cluster that is the most critical to relative positioning in the architecture,we propose a cluster relative positioning algorithm based on spatiotemporal correlation information.With the design idea of low cost and large-scale application,the algorithm uses intra-cluster ranging and the inertial navigation motion vector to construct the positioning equation and solves it through the Multidimensional Scaling(MDS)and Multiple Objective Particle Swarm Optimization(MOPSO)algorithms.The cluster formation is abstracted as a mixed direction-distance graph and the graph rigidity theory is used to analyze localizability conditions of the algorithm.We designed the cluster positioning simulation software and conducted localizability tests and positioning accuracy tests in diferent scenarios.Compared with the relative positioning algorithm based on Extended Kalman Filter(EKF),the algorithm proposed in this paper has more relaxed positioning conditions and can adapt to a variety of scenarios.It also has higher relative positioning accuracy,and the error does not accumulate over time.