Optimization of chemistry and process parameters for control of intermetallic formation in Mg sludges

Intermetallic formation in sludge during magnesium(Mg)melting,holding and high pressure die casting practices is a very important issue.But,very often it is overlooked by academia,original equipment manufacturers(OEM),metal ingot producers and even die casters.The aim of this study was to minimize the intermetallic formation in Mg sludge via the optimization of the chemistry and process parameters.The Al8Mn5 intermetallic particles were identified by the microstructure analysis based on the Al and Mn ratio.The design of experiment(DOE)technique,Taguchi method,was employed to minimize the intermetallic formation in the sludge of Mg alloys with various chemical compositions of Al,Mn,Fe,and different process parameters,holding temperature and holding time.The sludge yield(SY)and intermetallic size(IS)was selected as two responses.The optimum combination of the levels in terms of minimizing the intermetallic formation were 9 wt.%Al,0.15 wt.%Mn,0.001 wt.%(10 ppm)Fe,690℃ for the holding temperature and holding at 30 mins for the holding time,respectively.The best combination for smallest intermetallic size were 9 wt.%Al,0.15 wt.%Mn,0.001 wt.%(10 ppm)Fe,630℃ for the holding temperature and holding at 60 mins for the holding time,respectively.Three groups of sludge factors,Chemical Sludge(CSF),Physical Sludge(PSF)and Comprehensive Sludge Factors(and CPSF)were established for prediction of sludge yields and intermetallic sizes in Al-containing Mg alloys.The CPSF with five independent variables including both chemical elements and process parameters gave high accuracy in prediction,as the prediction of the PSF with only the two processing parameters of the melt holding temperature and time showed a relatively large deviation from the experimental data.The Chemical Sludge Factor was primarily designed for small ingot producers and die casters with a limited melting and holding capacity,of which process parameters could be fixed easily.The Physical Sludge Factor could be used for mass production with a single type of Mg alloy,in which the chemistry fluctuation might be negligible.In large Mg casting suppliers with multiple melting and holding furnaces and a number of Mg alloys in production,the Comprehensive Sludge Factor should be implemented to diminish the sludge formation.

Improved Particle Swarm Optimization for Parameter Identification of Permanent Magnet Synchronous Motor

In the process of identifying parameters for a permanent magnet synchronous motor,the particle swarm optimization method is prone to being stuck in local optima in the later stages of iteration,resulting in low parameter accuracy.This work proposes a fuzzy particle swarm optimization approach based on the transformation function and the filled function.This approach addresses the topic of particle swarmoptimization in parameter identification from two perspectives.Firstly,the algorithm uses a transformation function to change the form of the fitness function without changing the position of the extreme point of the fitness function,making the extreme point of the fitness function more prominent and improving the algorithm’s search ability while reducing the algorithm’s computational burden.Secondly,on the basis of themulti-loop fuzzy control systembased onmultiplemembership functions,it is merged with the filled function to improve the algorithm’s capacity to skip out of the local optimal solution.This approach can be used to identify the parameters of permanent magnet synchronous motors by sampling only the stator current,voltage,and speed data.The simulation results show that the method can effectively identify the electrical parameters of a permanent magnet synchronous motor,and it has superior global convergence performance and robustness.

Optimization Study of Active-Passive Heating System Parameters in Village Houses in the Southern Xinjiang Province

Aiming at the problems of large energy consumption and serious pollution of winter heating existing in the rural buildings in Southern Xinjiang,a combined active-passive heating system was proposed,and the simulation software was used to optimize the parameters of the system,according to the parameters obtained from the optimization,a test platform was built and winter heating test was carried out.The simulation results showed that the thickness of the air layer of 75 mm,the total area of the vent holes of 0.24 m^(2),and the thickness of the insulation layer of 120 mm were the optimal construction for the passive part;solar collector area of 28 m^(2),hot water storage tank volume of 1.4 m^(3),mass flow rate of 800 kg/h on the collector side,mass flow rate of 400 kg/h on the heat exchanger side,and output power of auxiliary heat source of 5∼9 kWwere the optimal constructions for active heating system.Test results showed that during the heating period,the system could provide sufficient heat to the room under different heating modes,and the indoor temperature reached over 18°C,which met the heating demand.The economic and environmental benefits of the system were analyzed,and the economic benefits of the systemwere better than coal-fired heating,and the CO_(2) emissionswere reduced by 3,292.25 kg compared with coalfiredheating.The results of the study showed that the combinedactive-passiveheating systemcouldeffectively solve the heating problems existing in rural buildings in Southern Xinjiang,and it also laid the theoretical foundation for the popularization of the combined heating systems.

Gray code based gradient-free optimization algorithm for parameterized quantum circuit

A Gray code based gradient-free optimization(GCO)algorithm is proposed to update the parameters of parameterized quantum circuits(PQCs)in this work.Each parameter of PQCs is encoded as a binary string,named as a gene,and a genetic-based method is adopted to select the offsprings.The individuals in the offspring are decoded in Gray code way to keep Hamming distance,and then are evaluated to obtain the best one with the lowest cost value in each iteration.The algorithm is performed iteratively for all parameters one by one until the cost value satisfies the stop condition or the number of iterations is reached.The GCO algorithm is demonstrated for classification tasks in Iris and MNIST datasets,and their performance are compared by those with the Bayesian optimization algorithm and binary code based optimization algorithm.The simulation results show that the GCO algorithm can reach high accuracies steadily for quantum classification tasks.Importantly,the GCO algorithm has a robust performance in the noise environment.

Enhancing photovoltaic power prediction using a CNN-LSTM-attention hybrid model with Bayesian hyperparameter optimization

Improving the accuracy of solar power forecasting is crucial to ensure grid stability,optimize solar power plant operations,and enhance grid dispatch efficiency.Although hybrid neural network models can effectively address the complexities of environmental data and power prediction uncertainties,challenges such as labor-intensive parameter adjustments and complex optimization processes persist.Thus,this study proposed a novel approach for solar power prediction using a hybrid model(CNN-LSTM-attention)that combines a convolutional neural network(CNN),long short-term memory(LSTM),and attention mechanisms.The model incorporates Bayesian optimization to refine the parameters and enhance the prediction accuracy.To prepare high-quality training data,the solar power data were first preprocessed,including feature selection,data cleaning,imputation,and smoothing.The processed data were then used to train a hybrid model based on the CNN-LSTM-attention architecture,followed by hyperparameter optimization employing Bayesian methods.The experimental results indicated that within acceptable model training times,the CNN-LSTM-attention model outperformed the LSTM,GRU,CNN-LSTM,CNN-LSTM with autoencoders,and parallel CNN-LSTM attention models.Furthermore,following Bayesian optimization,the optimized model demonstrated significantly reduced prediction errors during periods of data volatility compared to the original model,as evidenced by MRE evaluations.This highlights the clear advantage of the optimized model in forecasting fluctuating data.

Landslide susceptibility mapping(LSM)based on different boosting and hyperparameter optimization algorithms:A case of Wanzhou District,China

Boosting algorithms have been widely utilized in the development of landslide susceptibility mapping(LSM)studies.However,these algorithms possess distinct computational strategies and hyperparameters,making it challenging to propose an ideal LSM model.To investigate the impact of different boosting algorithms and hyperparameter optimization algorithms on LSM,this study constructed a geospatial database comprising 12 conditioning factors,such as elevation,stratum,and annual average rainfall.The XGBoost(XGB),LightGBM(LGBM),and CatBoost(CB)algorithms were employed to construct the LSM model.Furthermore,the Bayesian optimization(BO),particle swarm optimization(PSO),and Hyperband optimization(HO)algorithms were applied to optimizing the LSM model.The boosting algorithms exhibited varying performances,with CB demonstrating the highest precision,followed by LGBM,and XGB showing poorer precision.Additionally,the hyperparameter optimization algorithms displayed different performances,with HO outperforming PSO and BO showing poorer performance.The HO-CB model achieved the highest precision,boasting an accuracy of 0.764,an F1-score of 0.777,an area under the curve(AUC)value of 0.837 for the training set,and an AUC value of 0.863 for the test set.The model was interpreted using SHapley Additive exPlanations(SHAP),revealing that slope,curvature,topographic wetness index(TWI),degree of relief,and elevation significantly influenced landslides in the study area.This study offers a scientific reference for LSM and disaster prevention research.This study examines the utilization of various boosting algorithms and hyperparameter optimization algorithms in Wanzhou District.It proposes the HO-CB-SHAP framework as an effective approach to accurately forecast landslide disasters and interpret LSM models.However,limitations exist concerning the generalizability of the model and the data processing,which require further exploration in subsequent studies.

Particle Swarm Optimization-Based Hyperparameters Tuning of Machine Learning Models for Big COVID-19 Data Analysis

Analyzing big data, especially medical data, helps to provide good health care to patients and face the risks of death. The COVID-19 pandemic has had a significant impact on public health worldwide, emphasizing the need for effective risk prediction models. Machine learning (ML) techniques have shown promise in analyzing complex data patterns and predicting disease outcomes. The accuracy of these techniques is greatly affected by changing their parameters. Hyperparameter optimization plays a crucial role in improving model performance. In this work, the Particle Swarm Optimization (PSO) algorithm was used to effectively search the hyperparameter space and improve the predictive power of the machine learning models by identifying the optimal hyperparameters that can provide the highest accuracy. A dataset with a variety of clinical and epidemiological characteristics linked to COVID-19 cases was used in this study. Various machine learning models, including Random Forests, Decision Trees, Support Vector Machines, and Neural Networks, were utilized to capture the complex relationships present in the data. To evaluate the predictive performance of the models, the accuracy metric was employed. The experimental findings showed that the suggested method of estimating COVID-19 risk is effective. When compared to baseline models, the optimized machine learning models performed better and produced better results.

Parameters Optimization and Performance Evaluation of the Tuned Inerter Damper for the Seismic Protection of Adjacent Building Structures

In order to improve the seismic performance of adjacent buildings,two types of tuned inerter damper(TID)damping systems for adjacent buildings are proposed,which are composed of springs,inerter devices and dampers in serial or in parallel.The dynamic equations of TID adjacent building damping systems were derived,and the H2 norm criterion was used to optimize and adjust them,so that the system had the optimum damping performance under white noise random excitation.Taking TID frequency ratio and damping ratio as optimization parameters,the optimum analytical solutions of the displacement frequency response of the undamped structure under white noise excitation were obtained.The results showed that compared with the classic TMD,TID could obtain a better damping effect in the adjacent buildings.Comparing the TIDs composed of serial or parallel,it was found that the parallel TIDs had more significant advantages in controlling the peak displacement frequency response,while the H2 norm of the displacement frequency response of the damping system under the coupling of serial TID was smaller.Taking the adjacent building composed of two ten-story frame structures as an example,the displacement and energy collection time history analysis of the adjacent building coupled with the optimum design parameter TIDs were carried out.It was found that TID had a better damping effect in the full-time range compared with the classic TMD.This paper also studied the potential power of TID in adjacent buildings,which can be converted into available power resources during earthquakes.

Improving Prediction Efficiency of Machine Learning Models for Cardiovascular Disease in IoST-Based Systems through Hyperparameter Optimization

This study explores the impact of hyperparameter optimization on machine learning models for predicting cardiovascular disease using data from an IoST(Internet of Sensing Things)device.Ten distinct machine learning approaches were implemented and systematically evaluated before and after hyperparameter tuning.Significant improvements were observed across various models,with SVM and Neural Networks consistently showing enhanced performance metrics such as F1-Score,recall,and precision.The study underscores the critical role of tailored hyperparameter tuning in optimizing these models,revealing diverse outcomes among algorithms.Decision Trees and Random Forests exhibited stable performance throughout the evaluation.While enhancing accuracy,hyperparameter optimization also led to increased execution time.Visual representations and comprehensive results support the findings,confirming the hypothesis that optimizing parameters can effectively enhance predictive capabilities in cardiovascular disease.This research contributes to advancing the understanding and application of machine learning in healthcare,particularly in improving predictive accuracy for cardiovascular disease management and intervention strategies.

Optimization of AZ80 magnesium alloy squeeze cast process parameters using morphological matrix

The squeeze cast process parameters of AZ80 magnesium alloy were optimized by morphological matrix. Experiments were conducted by varying squeeze pressure, die pre-heat temperature and pressure duration using L9（33） orthogonal array of Taguchi method. In Taguchi method, a 3-level orthogonal array was used to determine the signal/noise ratio. Analysis of variance was used to determine the most significant process parameters affecting the mechanical properties. Mechanical properties such as ultimate tensile strength, elongation and hardness of the components were ascertained using multi variable linear regression analysis. Optimal squeeze cast process parameters were obtained.

High temperature deformation behavior and optimization of hot compression process parameters in TC11 titanium alloy with coarse lamellar original microstructure

The high temperature deformation behaviors of α＋β type titanium alloy TC11 （Ti-6.5Al-3.5Mo-1.5Zr-0.3Si） with coarse lamellar starting microstructure were investigated based on the hot compression tests in the temperature range of 950-1100 ℃ and the strain rate range of 0.001-10 s-1. The processing maps at different strains were then constructed based on the dynamic materials model, and the hot compression process parameters and deformation mechanism were optimized and analyzed, respectively. The results show that the processing maps exhibit two domains with a high efficiency of power dissipation and a flow instability domain with a less efficiency of power dissipation. The types of domains were characterized by convergence and divergence of the efficiency of power dissipation, respectively. The convergent domain in a＋fl phase field is at the temperature of 950-990 ℃ and the strain rate of 0.001-0.01 s^-1, which correspond to a better hot compression process window of α＋β phase field. The peak of efficiency of power dissipation in α＋β phase field is at 950 ℃ and 0.001 s 1, which correspond to the best hot compression process parameters of α＋β phase field. The convergent domain in β phase field is at the temperature of 1020-1080 ℃ and the strain rate of 0.001-0.1 s^-l, which correspond to a better hot compression process window of β phase field. The peak of efficiency of power dissipation in ℃ phase field occurs at 1050 ℃ over the strain rates from 0.001 s^-1 to 0.01 s^-1, which correspond to the best hot compression process parameters of ,8 phase field. The divergence domain occurs at the strain rates above 0.5 s^-1 and in all the tested temperature range, which correspond to flow instability that is manifested as flow localization and indicated by the flow softening phenomenon in stress-- strain curves. The deformation mechanisms of the optimized hot compression process windows in a＋β and β phase fields are identified to be spheroidizing and dynamic recrystallizing controlled by self-diffusion mechanism, respectively. The microstructure observation of the deformed specimens in different domains matches very well with the optimized results.

PROCESSING PARAMETER OPTIMIZATION OF FDM BASED ON ROBUST DESIGN

The influence of processing parameters on the precision of parts fabricated by fused deposition modeling （FDM） technology is studied based on a series of performed experiments. Processing parameters of FDM in terms of wire-width compensation, extrusion velocity, filing velocity, and layer thickness are chosen as the control fac- tors. Robust design analysis and multi-index fuzzy comprehensive assessment method are used to obtain the opti- mal parameters. Results show that the influencing degrees of these four factors on the precision of as-processed parts are different. The optimizations of individual parameters and their combined effects are of the same impor- tance for a high precision manufacturing.

Process parameters optimization of Ti-6Al-4V alloy sheet during hot stretch-creep forming

Hot stretch-creep forming （SCF） is a novel technique to produce hard-to-form thin-walled metal components. Comprehensively considering the analysis results of the springback angle, yield strength and microstructure, four hot SCF process parameters including temperature, stretch velocity, post stretch percentage and dwelling time of a Ti-6Al-4V alloy sheet were optimized using an orthogonal experiment. The results reveal that temperature is the most important factor on springback angle. The yield strength of the deformed material in 0° direction increases, while those in directions of 45° and 90° fluctuate around the original value. After hot SCF, the shape of some a phases changes from short thin grains to long slender ones, and the microhardness changes very little. The optimized parameters with temperature of 700 ℃, stretch velocity of 5 mm/min, post stretch percentage of 2% and dwelling time of 8 min are achieved finally.

Application of EBSD technique to ultrafine grained and nanostructured materials processed by severe plastic deformation:Sample preparation, parameters optimization and analysis

With the help of FESEM, high resolution electron backscatter diffraction can investigate the grains/subgrains as small as a few tens of nanometers with a good angular resolution （~0.5°）. Fast development of EBSD speed （up to 1100 patterns per second） contributes that the number of published articles related to EBSD has been increasing sharply year by year. This paper reviews the sample preparation, parameters optimization and analysis of EBSD technique, emphasizing on the investigation of ultrafine grained and nanostructured materials processed by severe plastic deformation （SPD）. Detailed and practical parameters of the electropolishing, silica polishing and ion milling have been summarized. It is shown that ion milling is a real universal and promising polishing method for EBSD preparation of almost all materials. There exists a maximum value of indexed points as a function of step size. The optimum step size depends on the magnification and the board resolution/electronic step size. Grains/subgrains and texture, and grain boundary structure are readily obtained by EBSD. Strain and stored energy may be analyzed by EBSD.

INTERNET-BASED MACHINING PARAMETER OPTIMIZATION AND MANAGEMENT SYSTEM FOR HIGH-SPEED MACHINING

The theory and its method of machining parameter optimization for high-speed machining are studied. The machining data collected from workshops, labs and references are analyzed. An optimization method based on the genetic algorithm (GA) is investigated. Its calculation speed is faster than that of traditional optimization methods, and it is suitable for the machining parameter optimization in the automatic manufacturing system. Based on the theoretical studies, a system of machining parameter management and optimization is developed. The system can improve productivity of the high-speed machining centers.

PARAMETERIZED-PROTOTYPE-BASED DYNAMIC OPTIMIZATION DESIGN FOR CAM PROFILE

Aiming at the problems in current cam profile optimization processes, such as simple dynamics models, limited geometric accuracy and low design automatization level, a new dynamic optimization mode is put forward. Based on the parameterization modeling technique of MSC. ADAMS platform, the different steps in current mode are reorganized, thus obtaining an upgraded mode called the ＂parameterized-prototype-based cam profile dynamic optimization mode＂. A parameterized prototype（PP） of valve mechanism is constructed in the course of dynamic optimization for cam profiles. Practically, by utilizing PP and considering the flexibility of the parts in valve mechanism, geometric accuracy and design automatization are improved.

Application of BP neural network model with fuzzy optimization in retrieval of biomass parameters

The retrieval of the biomass parameters from active/passive microwave remote sensing data （10.2 GHz） is performed based on an iterative inversion of BP neural network model with fuzzy optimization. The BP neural network is trained by a set of the measurements of active and passive remote sensing and the ground truth data versus Day of Year during growth. Once the network training is complete, the model can be used to retrieve the temporal variations of the biomass parameters from another set of observation data. The model was used in weights and microware observation data of wheat growth in 1989 to retrieve biomass parameters change of wheat growth this year. The retrieved biomass parameters correspond well with the real data of the growth, which shows that the BP model is scientific and sound.

Grain refinement of Mg-Al alloys by optimization of process parameters based on three-dimensional finite element modeling of roll casting

To study the influence of roll casting process parameters on temperature and thermal-stress fields for the AZ31 magnesium alloy sheets,three-dimensional geometric and 3D finite element models for roll casting were established based on the symmetry of roll casting by ANSYS software.Meshing method and smart-sizing algorithm were used to divide finite element mesh in ANSYS software.A series of researches on the temperature and stress distributions during solidification process with different process parameters were done by 3D finite element method.The temperatures of both the liquid-solid two-phase zone and liquid phase zone were elevated with increasing pouring temperature.With the heat transfer coefficient increasing,the two-phase region for liquid-solid becomes smaller.With the pouring temperature increasing and the increase of casting speed,the length of two-phase zone rises.The optimized of process parameters（casting speed 2 m/min,pouring temperature 640 ℃ and heat transfer coefficient 15 kW/（m2·℃） with the water pouring at roller exit was used to produce magnesium alloy AZ31 sheet,and equiaxed grains with the average grain size of 50 μm were achieved after roll casting.The simulation results give better understanding of the temperature variation in phase transformation zone and the formation mechanism of hot cracks in plates during roll casting and help to design the optimized process parameters of roll casting for Mg alloy.

Machine tool selection based on fuzzy evaluation and optimization of cutting parameters

The paper analyzes the factors influencing machine tool selection. By using fuzzy mathematics theory, we establish a theorietical model for optimal machine tool selection considering geometric features, clamping size, machining range, machining precision and surface roughness. By means of fuzzy comprehensive evaluation method, the membership degree of machine tool selection and the largest comprehensive evaluation index are determined. Then the reasonably automatic selection of machine tool is realized in the generative computer aided process planning （CAPP） system. Finally, the finite element model based on ABAQUS is established and the cutting process of machine tool is simulated. According to the theoretical and empirical cutting parameters and the curve of surface residual stress, the optimal cutting parameters can be determined.

IMPROVED PARTICLE SWARM OPTIMIZATION ALGORITHM FOR INTELLIGENTLY SETTING UAV ATTITUDE CONTROLLER PARAMETERS

An improved particle swarm optimization （PSO） algorithm is investigated in the optimization of the attitude controller parameters of unmanned aerial vehicle （UAV）. Considering the stagnation phenomenon in the later phase of the basic PSO algorithm caused by the diversity scarcity of particles, a modified PSO algorithm is presented. For the basic PSO algorithm, the velocity of each particle is adjusted according to the inertia motion, the swarm previous best position and its own previous best position. However, in the improved PSO algorithm, each particle only learns from another randomly selected particle with higher performance, besides keeping the inertia motion. The inertia weight of the improved PSO algorithm is a random number. The modification decreases the uncertain parameters of the algorithm, simplifies the learning mechanism of the particle, and enhances the diversity of the swarm. Furthermore, a UAV attitude control system is built, and the improved PSO algorithm is applied in the optimized tuning of four controller parameters. Simulation results show that the improved PSO algorithm has stronger global searching ability than the common PSO algorithms, and obtains better UAV attitude control parameters.