Multi-objective Optimization Of Process Parameters Research Articles

Machining performance analysis of wire-EDM for machining of titanium alloy using multi-objective optimization and machine learning approach

This study investigates the multi-objective optimization of process parameters in wire electrical discharge machining (WEDM) using titanium alloy grade 5 and zinc-coated brass microwire. The novelty lies in the comprehensive investigation of the effects of varying pulse on time (Ton), wire tension (WT), and wire feed rate (WF) on output responses, including surface roughness (SR), surface crack density (SCD), corner diameter (CD), and kerf width (KW). The Box-Behnken design, a sophisticated response surface methodology (RSM) technique, is employed to efficiently explore the complex relationships and interdependencies between these input and output parameters. The study's novel approach incorporates machine learning algorithms, including decision tree, light gradient boosting machine (LightGBM) and random forest, to predict the characteristics of the laser-cut components based on the input parameters. The contour plots generated provide valuable insights into the underlying patterns and associations between input and output features, aiding in the understanding of the WEDM process. The results reveal that the optimized values for SR, SCD, CD, and KW are obtained at specific machining conditions: Ton of 10 μs, WF of 3.79 m/min, and WT of 8 gf. Among the machine learning algorithms employed, random forest outperforms the others in predicting KW, SR, SCD and CD, exhibiting significantly lower mean squared error (MSE) and mean absolute error (MAE) values. This study contributes to the field of WEDM by providing a comprehensive analysis, incorporating advanced experimental design techniques and machine learning algorithms, which can aid in process optimization and quality control in manufacturing applications.

A Comparative Analysis of Single and Multi-objective Process Parameter Optimization of Dissimilar Metal Friction Welds

A Comparative Analysis of Single and Multi-objective Process Parameter Optimization of Dissimilar Metal Friction Welds

Multi-objective Optimization of Process Parameters for Surface Quality and Geometric Tolerances of AlSi10Mg Samples Produced by Additive Manufacturing Method Using Taguchi-Based Gray Relational Analysis

AbstractIn this study, it has been focused on examining the effects of production parameters on quality parameters such as surface roughness and geometric tolerances in the production of AlSi10Mg samples by the additive manufacturing method. The experimental design has been prepared according to the Taguchi L27 orthogonal array. As a result, in the production of samples, increasing laser power (P) contributed positively to surface roughness and diameter change, and increasing scanning distance (SD) negatively contributed to circularity change and concentricity. Further, it has been determined that increasing the scanning speed (SS) negatively affects the concentricity change of the produced samples. The optimum production parameters for surface roughness and diameter variation has been determined as A1B1C3. The optimum production parameters for circularity variation and concentricity have been determined as A3B3C1 and A3B1C1, respectively. According to the ANOVA analysis results, the most effective parameters for surface roughness, diameter change, circularity change and concentricity have been 53.22% P, 62.45% SD, 37.23% SS and 40.41% SD, respectively. Furthermore, as a result of the gray relationship analysis (GRA) performed for the output parameters, the optimum production parameter has been determined as A2B1C3.

Optimizing Time-Constrained Multi-Objective Process Parameters for Thin-Walled Maraging Steels Manufactured by Laser Powder Bed Fusion (LPBF)

Additive manufacturing is an innovative manufacturing process that enables complex topological structures and low-volume, high-variety production. One of the major adaptations of this method is in the tire industry. Thin-walled sipes slit the tires to improve drainage and traction. The material properties of thin-walled structures manufactured by additive manufacturing are different and more sensitive than those of conventional cube-shaped specimens. Thin-walled maraging steel specimens are considered to be able to model the relationship between the process parameters and the properties of the sipes adequately. Tire sipes are made of maraging steel. Maraging steels are a class of low-carbon high-alloy martensitic steel generally providing high strength, ductility, and good fracture toughness. In particular, these alloys exhibit a good combination of strength and toughness at elevated temperatures, which has been desirable for applications in aerospace and tooling. In order to consider productivity, multi-objective process parameter optimization with a build-time-constrained model is proposed.

Multi-Objective Process Parameter Optimization of Ultrasonic Rolling Combining Machine Learning and Non-Dominated Sorting Genetic Algorithm-II.

Ultrasonic rolling is an effective technique for enhancing surface integrity, and surface integrity is closely related to fatigue performance. The process parameters of ultrasonic rolling critically affect the improvement of surface integrity. This study proposes an optimization method for process parameters by combining machine learning (ML) with the NSGA-II. Five ML models were trained to establish relationships between process parameters and surface residual stress, hardness, and surface roughness by incorporating feature augmentation and physical information. The best-performing model was selected and integrated with NSGA-II for multi-objective optimization. Ultrasonic rolling tests based on a uniform design were performed, and a dataset was established. The objective was to maximize surface residual stress and hardness while minimizing surface roughness. For test specimens with an initial surface roughness of 0.54 µm, the optimized process parameters were a static pressure of 900 N, a spindle speed of 75 rpm, a feed rate of 0.19 mm/r, and rolling once. Using optimized parameters, the surface residual stress reached -920.60 MPa, surface hardness achieved 958.23 HV, surface roughness reduced to 0.32 µm, and contact fatigue life extended to 3.02 × 107 cycles, representing a 52.5% improvement compared to untreated specimens and an even more significant improvement over without parameter optimization.

Research on Multi-Objective Process Parameter Optimization Method in Hard Turning Based on an Improved NSGA-II Algorithm

To address the issue of local optima encountered during the multi-objective optimization process with the Non-dominated Sorting Genetic Algorithm II (NSGA-II) algorithm, this paper introduces an enhanced version of the NSGA-II. This improved NSGA-II incorporates polynomial and simulated binary crossover operators into the genetic algorithm’s crossover phase to refine its performance. For evaluation purposes, the classic ZDT benchmark functions are employed. The findings reveal that the enhanced NSGA-II algorithm achieves higher convergence accuracy and surpasses the performance of the original NSGA-II algorithm. When applied to the machining of the high-hardness material 20MnCrTi, four algorithms were utilized: the improved NSGA-II, the conventional NSGA-II, NSGA-III, and MOEA/D. The experimental outcomes show that the improved NSGA-II algorithm delivers a more optimal combination of process parameters, effectively enhancing the workpiece’s surface roughness and material removal rate. This leads to a significant improvement in the machining quality of the workpiece surface, demonstrating the superiority of the improved algorithm in optimizing machining processes.

Analysis and optimization of the heat transfer behavior in the melt-spinning process of Nd-Fe-B ribbons

Heat transfer plays a significant role on the quality of Nd-Fe-B ribbons in the melt-spinning (MS) process. In this paper, the heat transfer behavior in the MS process of Nd-Fe-B ribbons was investigated by experiment and simulation. A full flow channel heat transfer model with high accuracy is established using the “fluid-thermal” coupling method. The temperature distribution of the cooling roller and fluid field in steady-state is obtained. The simulated and experimental results of the outlet temperature are compared and the relative error is within 5%. The microstructures of the free surface and roller-sticking surface of Nd-Fe-B melt-spun ribbons are characterized by FE-SEM, and the refined grains are formed on the roller-sticking surface of Nd-Fe-B ribbons due to rapid solidification caused by the heat transfer from the roller. Moreover, a multi-nozzle structure is proposed for the MS process. The temperature distribution on the surface of the cooling roller in the axial direction is more uniform compared with the original single-nozzle structure, and the average convective heat transfer coefficient is increased by about 1.27 times after the modification of multi-nozzle structure, with a productivity of three times. Finally, the experimental design method of Latin hypercube sampling response surface design is used to obtain the response surface relationships of rotational speed, inlet flow rate, and water inlet temperature on the surface temperature of the cooling roller, respectively. NSGA-II multi-objective genetic algorithm (MOGA) is adopted for multi-objective optimization of process parameters. The optimized combination of process parameters is obtained with a relative error of about 0.41%. The research results are helpful to understand the heat transfer behaviors in the MS process of Nd-Fe-B ribbons, improve the utilization rate of the cooling roller and enhance the production efficiency in the actual application.

Multi-Objective Optimization of Process Parameters in Laser DED Ni-Based Powder on Steel Rail Using Response Surface Design

With the rise of global industrialization, the requirements for the operating speed and carrying capacity of high-speed trains are increasingly higher. Because the wear and tear of rails gradually increases during the running of high-speed trains, strengthening or repairing rail surfaces is of paramount significance. Laser-directed energy deposition (DED) exhibits significant advantages in improving surface hardness, corrosion resistance, and abrasion resistance. Because of the multiple interacting optimization objectives, the development of a multi-objective optimization method for process parameters is significant for improving DED deposition quality. Response surface design employs multivariate quadratic regression equations to fit the functional relationship between the factors and the responses, which can be employed to find the optimal process parameters and solve multivariate problems. This study develops a multi-objective optimization model with response surface design and 2D process mappings to visually analyze the effects of scanning speed, laser power, and powder feed rate on aspect ratio, dilution rate, and microhardness. The optimal combination of process parameters for Ni-based alloys on U71Mn rail is a laser power of 431 W, a scanning speed of 5.34 mm/s, and a powder feed rate of 1.03 r/min. In addition, a multi-physics field finite element model is developed to analyze the evolution mechanism of the microstructure from the bottom to the top of the single track. This study can provide theoretical and technical support for the surface strengthening or repair of U71Mn rail.

Multiobjective optimization of process parameters of AZ91D/AgNPs/TiO2 composite fabricated by friction stir processing using response surface methodology and desirability

PurposeThis paper aims to determine the optimum parametric settings for yielding superior mechanical properties, namely, ultimate tensile strength (UTS), yield strength (YS) and percentage elongation (EL) of AZ91D/AgNPs/TiO2 hybrid composite fabricated by friction stir processing.Design/methodology/approachAn empirical model has been developed to govern crucial influencing parameters, namely, rotation speed (RS), tool transverse speed (TS), number of passes (NPS) and reinforcement fraction (RF) or weight percentage. Box Behnken design (BBD) with four input parameters and three levels of each parameter was used to design the experimental work, and analysis of variance (ANOVA) was used to check the acceptability of the developed model. Desirability function analysis (DFA) for a multiresponse optimization approach is integrated with response surface methodology (RSM). The individual desirability index (IDI) was calculated for each response, and a composite desirability index (CDI) was obtained. The optimal parametric settings were determined based on maximum CDI values. A confirmation test is also performed to compare the actual and predicted values of responses.FindingsThe relationship between input parameters and output responses (UTS, YS, and EL) was investigated using the Box-Behnken design (BBD). Silver nanoparticles (AgNPs) and nano-sized titanium dioxide (TiO2) enhanced the ultimate tensile strength and yield strength. It was observed that the inclusion of AgNPs led to an increase in ductility, while the increase in the weight fraction of TiO2 resulted in a decrease in ductility.Practical implicationsAZ91D/AgNPs/TiO2 hybrid composite finds enormous applications in biomedical implants, aerospace, sports and aerospace industries, especially where lightweight materials with high strength are critical.Originality/valueIn terms of optimum value through desirability, the experimental trials yield the following results: maximum value of UTS (318.369 MPa), maximum value of YS (200.120 MPa) and EL (7.610) at 1,021 rpm of RS, 70 mm/min of TS, 4 NPS and level 3 of RF.

Multi-objective optimization of process parameters for laser metal deposition of NiTi shape memory alloy based on neural network and genetic algorithm

Multi-objective optimization of process parameters for laser metal deposition of NiTi shape memory alloy based on neural network and genetic algorithm

Multi-objective optimization of process parameters during friction stir welding of similar AA6061 using MOORA

This work is an attempt to select the optimum process parameters for friction stir welding of similar AA6061 aluminum alloy based on multiple criteria decision-making approach. The friction stir welding experiments have been conducted according to the orthogonal L9 array and the chosen input parameters are tool rotational speed, feed, and tilt angle. The responses measured are tensile strength, hardness, and % of elongation of welded joint. The multi-criteria decision-making technique namely multi-objective optimization based on the ratio analysis (MOORA) is used to find the optimum process parameters combination. The optimum conditions are tool rotational speed of 1120 rpm, feed of 30 mm/rev and tilt angle at 1 o.

Multi-objective optimization of process parameters of laser cladding 15-5PH alloy powder based on gray-fuzzy taguchi approach

Laser cladding is a new surface treatment technology that is widely used for surface modification of metal parts, and the high quality of the surface geometry of the cladding layer can save a lot of resources for the company. To obtain high quality of the clad layer, the L25 Taguchi experiment of laser cladding process parameters was designed to laser-clad a single 15-5PH layer on the surface of 45# steel; the effect of process parameters on the surface morphology and dilution rate of the coating was determined by ANOVA; the optimal combination of process parameters was obtained by combining gray correlation and fuzzy inference system method. The ANOVA results show that the scanning speed among the laser cladding process parameters plays a key role in obtaining the best superposition of the four geometrical features of the cladding layer simultaneously; With the optimization objectives of larger clad width and height, smaller clad depth, and 30% dilution rate, the optimal combination of process parameters, (P: 600W, V: 500 mm min−1, F −1 : 1.3 r min−1), obtained based on the Gray-fuzzy Taguchi Approach, was compared and analyzed to find a significant improvement in the geometric quality characteristics of the optimized clad layer. The analysis of microstructure, physical phase, hardness, wear resistance and corrosion resistance showed that the 15-5PH clad layer was able to effectively enhance the surface properties of the 12Cr13 substrate. The optimization method proposed in this study can solve the problem of parameter optimization in the industrial multi-parameter and multi-response processes.

Development of AHP-embedded Deng’s hybrid MCDM model in micro-EDM using carbon-coated electrode

Abstract The use of thin film-coated micro-tool electrode introduced a new technical solution to bring the best technical–economic efficiency in the field of non-conventional machining processes. Multi-objective optimization of process parameters in micro-electrical discharge machining (EDM) is very limited with the help of thin film-coated micro-tool, which brought benefits for the industry. In this research work, the technological parameters such as voltage (V), spindle rotation, and capacitance (C) in micro-EDM using carbon-coated electrode were optimized, and Z-coordinate depth of cut and tool wear rate were selected as response variables. Taguchi is combined with Deng’s method to solve this multi-objective decision problem. The results showed that Taguchi–Deng’s method is the right solution for multi-target decision in micro-EDM using the coated electrode. C is the strongest influence on optimal efficiency, and it is the smallest with V. The machining quality under optimal conditions is improved.

Generative machine learning-based multi-objective process parameter optimization towards energy and quality of injection molding.

The high energy intensity and rigorous quality demand of injection molding have received significant interest under the background of the soaring production of global plastic industry. As multiple parts can be produced in a multi-cavity mold during one operation cycle, the weight differences of these parts have been demonstrated to reflect their quality performance. In this regard, this study incorporated this fact and developed a generative machine learning-based multi-objective optimization model. Such model can predict the qualification of parts produced under different processing variables and further optimize processing variables of injection molding for minimal energy consumption and weight difference amongst parts in one cycle. Statistical assessment via F1-score and R2 was performed to evaluate the performance of the algorithm. In addition, to validate the effectiveness of our model, we conducted physical experiments to measure the energy profile and weight difference under varying parameter settings. Permutation-based mean square error reduction was adopted to specify the importance of parameters affecting energy consumption and quality of injection molded parts. Optimization results indicated that the processing parameters optimization could reduce ~ 8% energy consumption and ~ 2% weight difference compared with the average operation practices. Maximum speed and first-stage speed were identified as the dominating factors affecting quality performance and energy consumption, respectively. This study could contribute to the quality assurance of injection molded parts and facilitate energy efficient and sustainable plastic manufacturing.

Multi-Objective Optimization of Process Parameters in Milling of 17-4 PH Stainless Steel using Taguchi-based Gray Relational Analysis

Multi-Objective Optimization of Process Parameters in Milling of 17-4 PH Stainless Steel using Taguchi-based Gray Relational Analysis

Multi-Objective Optimization of Process Parameters during Micro-Milling of Nickel-Based Alloy Inconel 718 Using Taguchi-Grey Relation Integrated Approach

This research investigates the machinability of Inconel 718 under conventional machining speeds using three different tool coatings in comparison with uncoated tool during milling operation. Cutting speed, feed rate and depth of cut were selected as variable machining parameters to analyze output responses including surface roughness, burr formation and tool wear. It was found that uncoated and AlTiN coated tools resulted in lower tool wear than nACo and TiSiN coated tools. On the other hand, TiSiN coated tools resulted in highest surface roughness and burr formation. Among the three machining parameters, feed was identified as the most influential parameter affecting burr formation. Grey relational analysis identified the most optimal experimental run with a speed of 14 m/min, feed of 1 μm/tooth, and depth of cut of 70 μm using an AlTiN coated tool. ANOVA of the regression model identified the tool coating parameter as most effective, with a contribution ratio of 41.64%, whereas cutting speed and depth of cut were found to have contribution ratios of 18.82% and 8.10%, respectively. Experimental run at response surface optimized conditions resulted in reduced surface roughness and tool wear by 18% and 20%, respectively.

Applying Evolutionary Multitasking for Process Parameter Optimization in Polymerization Process of Carbon Fiber Production

Carbon fiber is becoming a key material for engineering applications due to its excellent comprehensive properties. The process parameter optimization is an important step in the polymerization process of carbon fiber production. At present, most of the research on process parameter optimization is usually carried out on a single production line, without considering the correlation between optimization problems. In this paper, a multiobjective mechanism model for the co-optimization of the polymerization process of carbon fiber production is established. Each of these submodels is a multiobjective process parameter optimization task, corresponding to the polymerization process of a production line. In order to solve the model effectively, we also designed an evolutionary multitasking algorithm based on transfer learning, which reuses the past experiences of one task to generate a population pool for the next iteration of another task, enabling explicit genetic transfer between different tasks and accelerating the population convergence speed. The proposed multitasking framework for operation optimization has been conducted on 10 different production conditions of the polymerization process. Experimental results show that compared with other implicit and explicit genetic algorithms, this algorithm is very competitive in generating effective solutions. This research provides important support for process parameter optimization and manufacturing of carbon fiber production, which will help engineers and technicians to make informed decisions.

Multi-objective optimization of process parameters of a hybrid IR-vibro fluidized bed dryer using RSM-DF and RSM-GA for recovery of bioactive compounds from pumpkin seeds

Multi-objective optimization of process parameters of a hybrid IR-vibro fluidized bed dryer using RSM-DF and RSM-GA for recovery of bioactive compounds from pumpkin seeds

Multi-Objective Optimization of Process Parameters of 45 Steel Laser Cladding Ni60PTA Alloy Powder

When laser cladding is used to repair parts, the interaction of parameters has a significant influence on equipment performance. In order to explore the process parameters and quality of Ni60PTA coating, the statistical relationship between the process parameters (laser power, scanning speed, and powder feeding rate) and the responses (dilution ratio, ratio of layer width to height, and contact angle) was established by experiments using the response surface method (RSM) and variance analysis. The results show that the laser power is the dominant factor affecting the dilution ratio. However, the scanning speed has the greatest influence on the ratio of layer width to height and contact angle. These experimental results show that the proposed model can predict the actual data. In addition, the microstructure and microhardness of the samples prepared with the optimum process parameters were characterized. The results show that the quality of the cladding layer is good without cracks, deformation, and pores. The microstructure of the cladding zone is mainly composed of γ (Ni), FeNi3, M (M = Fe, Ni, Cr)23C6, M7C3, and CrB. The average microhardness of the coating is about 620 HV0.2, which is about 3.1 times that of 45 steel substrate.

Investigation of TiAlN, AlTiN, and TiAlSiN Coated Inserts on the Machining Performance of AISI 420 Steel and Multi-Objective Optimization of Process Parameters

Investigation of TiAlN, AlTiN, and TiAlSiN Coated Inserts on the Machining Performance of AISI 420 Steel and Multi-Objective Optimization of Process Parameters