Search results

Surface roughness has a serious impact on the fatigue strength, wear resistance and life of mechanical products. Realizing the evolution of surface quality through theoretical modeling takes a lot of effort. To predict the surface roughness of milling processing, this paper aims to construct a neural network based on deep learning and data augmentation.

This study proposes a method consisting of three steps. Firstly, the machine tool multisource data acquisition platform is established, which combines sensor monitoring with machine tool communication to collect processing signals. Secondly, the feature parameters are extracted to reduce the interference and improve the model generalization ability. Thirdly, for different expectations, the parameters of the deep belief network (DBN) model are optimized by the tent-SSA algorithm to achieve more accurate roughness classification and regression prediction.

The adaptive synthetic sampling (ADASYN) algorithm can improve the classification prediction accuracy of DBN from 80.67% to 94.23%. After the DBN parameters were optimized by Tent-SSA, the roughness prediction accuracy was significantly improved. For the classification model, the prediction accuracy is improved by 5.77% based on ADASYN optimization. For regression models, different objective functions can be set according to production requirements, such as root-mean-square error (RMSE) or MaxAE, and the error is reduced by more than 40% compared to the original model.

A roughness prediction model based on multiple monitoring signals is proposed, which reduces the dependence on the acquisition of environmental variables and enhances the model's applicability. Furthermore, with the ADASYN algorithm, the Tent-SSA intelligent optimization algorithm is introduced to optimize the hyperparameters of the DBN model and improve the optimization performance.

Fused Filament Fabrication (FFF) is one of the growing technologies in additive manufacturing, that can be used in a number of applications. In this method, process parameters can be customized and their simultaneous variation has conflicting impacts on various properties of printed parts such as dimensional accuracy (DA) and surface finish. These properties could be improved by optimizing the values of these parameters.

In this paper, four process parameters, namely, print speed, build orientation, raster width, and layer height which are referred to as “input variables” were investigated. The conflicting influence of their simultaneous variations on the DA of printed parts was investigated and predicated. To achieve this goal, a hybrid Genetic Algorithm – Artificial Neural Network (GA-ANN) model, was developed in C#.net, and three geometries, namely, U-shape, cube and cylinder were selected. To investigate the DA of printed parts, samples were printed with a central through hole. Design of Experiments (DoE), specifically the Rotational Central Composite Design method was adopted to establish the number of parts to be printed (30 for each selected geometry) and also the value of each input process parameter. The dimensions of printed parts were accurately measured by a shadowgraph and were used as an input data set for the training phase of the developed ANN to predict the behavior of process parameters. Then the predicted values were used as input to the Desirability Function tool which resulted in a mathematical model that optimizes the input process variables for selected geometries. The mean square error of 0.0528 was achieved, which is indicative of the accuracy of the developed model.

The results showed that print speed is the most dominant input variable compared to others, and by increasing its value, considerable variations resulted in DA. The inaccuracy increased, especially with parts of circular cross section. In addition, if there is no need to print parts in vertical position, the build orientation should be set at 0° to achieve the highest DA. Finally, optimized values of raster width and layer height improved the DA especially when the print speed was set at a high value.

By using ANN, it is possible to investigate the impact of simultaneous variations of FFF machines’ input process parameters on the DA of printed parts. By their optimization, parts of highly accurate dimensions could be printed. These findings will be of significant value to those industries that need to produce parts of high DA on FFF machines.

The criteria importance through intercriteria correlation (CRITIC) and range of value (ROV) combined methods were used to determine a single index for all multiple responses.

This paper used cold metal transfer (CMT) and pulse metal-inert gas (MIG) welding processes to study the weld-on-bead geometry of AA2099-T86 alloy. This study used Taguchi's approach to find the optimal setting of the input welding parameters. The welding current, welding speed and contact-tip-to workpiece distance were the input welding parameters for finding the output responses, i.e. weld penetration, dilution and heat input. The L9 orthogonal array of Taguchi's approach was used to find out the optimal setting of the input parameters.

The optimal input welding parameters were determined with combined output responses. The predicted optimum welding input parameters were validated through confirmation tests. Analysis of variance showed that welding speed is the most influential factor in determining the weld bead geometry of the CMT and pulse MIG welding techniques.

The heat input and weld bead geometry are compared in both welding processes. The CMT welding samples show superior defect-free weld beads than pulse MIG welding due to lesser heat input and lesser dilution.

This study aims to investigate the optimal process parameters of the wire-cut electrical discharge machining (WCEDM) for the machining of the GZR-AA7475 hybrid metal matrix composite (HMMC). HMMCs are prepared with 2 Wt.% graphite and 4 Wt.% zirconium dioxide reinforced with aluminium alloy 7475 (GZR-AA7475) composite by using the stir casting method. The objective is to enhance the mechanical properties of the material while preserving its unique features. WCEDM with a 0.18 mm molybdenum wire electrode is used for machining the composite.

To conduct experimental studies, a Taguchi L27 orthogonal array was adopted. Input variables such as peak current (I_p), pulse-on-time (T_ON) and flushing pressure (P_F) were used. The effect of process parameters on the output responses, such as material removal rate (MRR), surface roughness rate (SRR) and wire wear ratio (WWR), were investigated. The grey relational analysis (GRA) is used to obtain the optimal combination of the process parameters. Analysis of variance (ANOVA) was also used to identify the significant process parameters affecting the output responses.

Results from the current study concluded that the optimal condition for grey relational grade is obtained at T_ON = 105 µs, I_p = 100 A and P_F = 90 kg/cm². Peak current is the most prominent parameter influencing the MRR, whereas SRR and WRR are highly influenced by flushing pressure.

Identifying the optimal process parameters in WCEDM for machining of GZR-AA7475 HMMC. ANOVA and GRA are used to obtain the optimal combination of the process parameters.

In this study, the central objective is to foresee stock market signals with the use of a proper structure to achieve the highest accuracy possible. For this purpose, three hybrid models have been developed for the stock markets which are a combination of support vector machine (SVM) with meta-heuristic algorithms of particle swarm optimization (PSO), imperialist competition algorithm (ICA) and genetic algorithm (GA).All the analyses are technical and are based on the Japanese candlestick model.

Further as per the results achieved, the most suitable algorithm is chosen to anticipate sell and buy signals. Moreover, the authors have compared the results of the designed model validations in this study with basic models in three articles conducted in the past years. Therefore, SVM is examined by PSO. It is used as a classification agent to search the problem-solving space precisely and at a faster pace. With regards to the second model, SVM and ICA are tested to stock market timing, in a way that ICA is used as an optimization agent for the SVM parameters. At last, in the third model, SVM and GA are studied, where GA acts as an optimizer and feature selection agent.

As per the results, it is observed that all new models can predict accurately for only 6 days; however, in comparison with the confusion matrix results, it is observed that the SVM-GA and SVM-ICA models have correctly predicted more sell signals, and the SCM-PSO model has correctly predicted more buy signals. However, SVM-ICA has shown better performance than other models considering executing the implemented models.

In this study, the data for stock market of the years 2013–2021 were analyzed; the long length of timeframe makes the input data analysis challenging as they must be moderated with respect to the conditions where they have been changed.

In this study, two methods have been developed in a candlestick model; they are raw-based and signal-based approaches in which the hit rate is determined by the percentage of correct evaluations of the stock market for a 16-day period.

Traditional multivariable grey prediction models define the background-value coefficients of the dependent and independent variables uniformly, ignoring the differences between their physical properties, which in turn affects the stability and reliability of the model performance.

A novel multivariable grey prediction model is constructed with different background-value coefficients of the dependent and independent variables, and a one-to-one correspondence between the variables and the background-value coefficients to improve the smoothing effect of the background-value coefficients on the sequences. Furthermore, the fractional order accumulating operator is introduced to the new model weaken the randomness of the raw sequence. The particle swarm optimization (PSO) algorithm is used to optimize the background-value coefficients and the order of the model to improve model performance.

The new model structure has good variability and compatibility, which can achieve compatibility with current mainstream grey prediction models. The performance of the new model is compared and analyzed with three typical cases, and the results show that the new model outperforms the other two similar grey prediction models.

This study has positive implications for enriching the method system of multivariable grey prediction model.

In many of today’s manufacturing industries, such as automobile, aerospace, defence, die and mould making, medical and electrical discharge machining (EDM) has emerged as an effective material removal process. In this process, a series of discontinuous electric discharges is used for removing material from the workpiece in the form of craters generating a replica of the tool into the workpiece in a dielectric environment. Appropriate selection of the tool electrode material and combination of input parameters is an important requirement for performance enhancement of an EDM process. This paper aims to optimize an EDM process using single-valued neutrosophic grey relational analysis using Cu-multi-walled carbon nanotube (Cu-MWCNT) composite tool electrode.

This paper proposes the application of grey relational analysis (GRA) in a single-valued neutrosophic fuzzy environment to identify the optimal parametric intermix of an EDM process while considering Cu-MWCNT composite as the tool electrode material. Based on Taguchi’s L9 orthogonal array, nine experiments are conducted at varying combinations of four EDM parameters, i.e. pulse-on time, duty factor, discharge current and gap voltage, with subsequent measurement of two responses, i.e. material removal rate (MRR) and tool wear rate (TWR). The electrodeposition process is used to fabricate the Cu-MWCNT composite tool.

It is noticed that both the responses would be simultaneously optimized at higher levels of pulse-on time (38 µs) and duty factor (8), moderate level of discharge current (5 A) and lower level of gap voltage (30 V). During bi-objective optimization (maximization of MRR and minimization of TWR) of the said EDM process, the achieved values of MRR and TWR are 243.74 mm³/min and 0.001034 g/min, respectively.

Keeping in mind the type of response under consideration, their measured values for each of the EDM experiments are expressed in terms of linguistic variables which are subsequently converted into single-valued neutrosophic numbers. Integration of GRA with single-valued neutrosophic sets would help in optimizing the said EDM process with the Cu-MWCNT composite tool while simultaneously considering truth-membership, indeterminacy membership and falsity-membership degrees in a human-centric uncertain decision-making environment.

The construction industry is tasked with creating sustainable, efficient and cost-effective buildings. This study aims to develop a building information modeling (BIM)-based multiobjective optimization (MOO) model integrating the nondominated sorting genetic algorithm III (NSGA-III) to enhance sustainability. The goal is to reduce embodied energy and cost in the design process.

Through a case study research method, this study uses BIM, NSGA-III and real-world data in five phases: literature review, identification of factors, BIM model development, MOO model creation and validation in the architecture, engineering and construction sectors.

The innovative BIM-based MOO model optimizes embodied energy and cost to achieve sustainable construction. A commercial building case study validation showed a reduction of 30% in embodied energy and 21% in cost. This study validates the model’s effectiveness in integrating sustainability goals, enhancing decision-making, collaboration, efficiency and providing superior assessment.

This model delivers a unified approach to sustainable design, cutting carbon footprint and strengthening the industry’s ability to attain sustainable solutions. It holds potential for broader application and future integration of social and economic factors.

The research presents a novel BIM-based MOO model, uniquely focusing on sustainable construction with embodied energy and cost considerations. This holistic and innovative framework extends existing methodologies applicable to various buildings and paves the way for additional research in this area.

The proposed model has been aimed to predict stock market signals by designing an accurate model. In this sense, the stock market is analysed by the technical analysis of Japanese Candlestick, which is combined by the following meta heuristic algorithms: support vector machine (SVM), meta-heuristic algorithms, particle swarm optimization (PSO), imperialist competition algorithm (ICA) and genetic algorithm (GA).

In addition, among the developed algorithms, the most effective one is chosen to determine probable sell and buy signals. Moreover, the authors have proposed comparative results to validate the designed model in this study with the same basic models of three articles in the past. Hence, PSO is used as a classification method to search the solution space absolutelyand with the high speed of running. In terms of the second model, SVM and ICA are examined by the time. Where the ICA is an improver for the SVM parameters. Finally, in the third model, SVM and GA are studied, where GA acts as optimizer and feature selection agent.

Results have been indicated that, the prediction accuracy of all new models are high for only six days, however, with respect to the confusion matrixes results, it is understood that the SVM-GA and SVM-ICA models have correctly predicted more sell signals, and the SCM-PSO model has correctly predicted more buy signals. However, SVM-ICA has shown better performance than other models considering executing the implemented models.

In this study, the authors to analyze the data the long length of time between the years 2013–2021, makes the input data analysis challenging. They must be changed with respect to the conditions.

In this study, two methods have been developed in a candlestick model, they are raw based and signal-based approaches which the hit rate is determined by the percentage of correct evaluations of the stock market for a 16-day period.

Material extrusion-based additive manufacturing is a prominent manufacturing technique to fabricate complex geometrical three-dimensional (3D) parts. Despite the indisputable advantages of material extrusion-based technique, the poor surface and subsurface integrity hinder the industrial application of this technology. The purpose of this study is introducing the hot air jet treatment (HAJ) technique for surface treatment of additive manufactured parts.

In the presented research, novel theoretical formulation and finite element models are developed to study and model the polishing mechanism of printed parts surface through the HAJ technique. The model correlates reflow material volume, layer width and layer height. The reflow material volume is a function of treatment temperature, treatment velocity and HAJ velocity. The values of reflow material volume are obtained through the finite element modeling model due to the complexity of the interactions between thermal and mechanical phenomena. The theoretical model presumptions are validated through experiments, and the results show that the treatment parameters have a significant impact on the surface characteristics, hardness and dimensional variations of the treated surface.

The results demonstrate that the average value of error between the calculated theoretical results and experimental results is 14.3%. Meanwhile, the 3D plots of Ra and Rq revealed that the maximum values of Ra and Rq reduction percentages at 255°C, 270°C, 285°C and 300°C treatment temperatures are (35.9%, 33.9%), (77.6%,76.4%), (94%, 93.8%) and (85.1%, 84%), respectively. The scanning electron microscope results illustrate three different treatment zones and the treatment-induced and manufacturing-induced entrapped air relief phenomenon. The measured results of hardness variation percentages and dimensional deviation percentages at different regimes are (8.33%, 0.19%), (10.55%, 0.31%) and (−0.27%, 0.34%), respectively.

While some studies have investigated the effect of the HAJ process on the structural integrity of manufactured items, there is a dearth of research on the underlying treatment mechanism, the integrity of the treated surface and the subsurface characteristics of the treated surface.