Fault location in distribution networks is a major challenge that needs to be addressed in power distribution systems. Currently, fault location methods based on matrix algorithms, genetic algorithms, deep learning, and other algorithms have received wide attention from the industry. However, such methods have some drawbacks: (1) they require high accuracy in fault information uploads, which can lead to low fault tolerance; (2) they tend to converge early and get stuck in local optimal solutions; (3) they involve high computational complexity, leading to location delays. In this study, we propose a fault location framework based on recurrent neural network (RNN) and transfer learning. In this method, we first encode the information data collected from distribution terminals, and then use RNN to establish a nonlinear mapping relationship between fault features and fault location intervals, which effectively improves fault tolerance and reduces misjudgment issues. We then use transfer learning to load the pre-trained model onto the target task to address the problem of insufficient data for fault location in distribution networks. Experimental results show that after 15 rounds of training, our T-RNN model has achieved over 80% accuracy. Benefiting from Glorot weight initialization adopted after transfer learning, the model achieves good performance early on compared to the BP model, converges faster, and ultimately achieves a prediction accuracy of 96.5%.
This paper examines the current state of the Enterprise Marketing Ecosystem (EME), especially in the context of Digital Transformation (DT), highlighting both the challenges and opportunities it presents. A significant focus is placed on the potential of genetic algorithms to address the complex optimization problems inherent in this transformation. The core issues faced by enterprises in their digital marketing evolution are elaborated, setting the stage for the exploration of genetic algorithms in this domain. The research delves into the specific steps of the proposed method, utilizing the multi-objective genetic algorithm NSGA-II to optimize various aspects of market strategies. The methodology includes the generation of an initial population, evaluation of fitness according to the tailored needs of the marketing ecosystem, selection, crossover, and mutation operations, followed by the formation of a new generation of solutions. The termination criteria of the algorithm are also discussed. Experimental results are presented, demonstrating the effectiveness of the genetic algorithm in enhancing the DT of the EME. Comparisons with traditional approaches reveal significant improvements in various key performance metrics, underscoring the algorithm’s capability in navigating the complexities of digital marketing optimization.
Building Information Modeling (BIM) technology has revolutionized the architectural and construction industries by providing detailed digital representations of buildings, enhancing design efficiency and project management. Despite its widespread application, the utilization of BIM in optimizing interior space planning, particularly in boutique accommodations like guesthouses, remains underexplored. This research addresses the gap by introducing a novel method for interior environment space planning of guesthouses based on the topological relationships derived from BIM data. This study developed a new algorithm that utilizes detailed topology information from BIM in order to make space planning decisions more efficiently, thereby improving space utilization efficiency and guest experience. Through a comprehensive analysis of BIM topological relationships and the application of advanced optimization techniques, our method aims to optimize the use of space while considering the unique constraints and requirements of guesthouse environments. The proposed algorithm demonstrates significant improvements in spatial efficiency and design quality when tested against traditional planning methods on real-world BIM datasets. This research not only contributes a novel approach to the field of architectural design and planning but also offers practical implications for the enhancement of interior spaces in guesthouses, potentially influencing future applications of BIM technology in the hospitality industry.
Recently, auditors have used audit risk models’ conceptual tools to assess and control the many risks that could occur during an audit. The tool guides the auditor in determining the necessary evidence for each relevant allegation and the required categories of evidence. The importance of refining audit risk assessment models depends on the crucial role that these models perform in allocating resources and reducing financial disparities. The challenging characteristic of such an audit risk assessment model is that inaccurate information can lead to incorrect risk assessments, legal frameworks and failure to detect material misstatements in financial statements. Hence, in this research, BP neural network-enabled machine learning (BPNN-ML) technologies have been improved for the audit risk assessment model. In that financial disparity, the regression algorithm was used to establish the audit risk assessment for data processing and entirely monitor it. The suggested method provides a flexible framework that may be utilized by a wide range of organizations, including global enterprises and financial institutions, to optimize audit processes and ensure regulatory compliance. This research adds to advancing auditing procedures and regulatory compliance efforts in contemporary company contexts by addressing the issues inherent in traditional methods and proposing a practical approach to these concerns. The experimental analysis of BPNN-ML outperforms physical monitoring in terms of feature importance ranking analysis, contextual adaptability analysis, sensitivity analysis, performance analysis and optimized risk assessment analysis.
In order to address inefficiencies in the inspection path planning of metering equipment and minimize inspection path lengths, this study proposes a novel optimization method based on the quantum annealing algorithm. A mathematical model for metering equipment inspection path planning is developed, accompanied by a new qubit measurement and state update mechanism designed to enhance algorithm convergence speed. Simulation experiments validate the effectiveness of the proposed algorithm, demonstrating its ability to plan inspection paths under diverse conditions while achieving the shortest path lengths and maintaining strong global convergence. The results highlight the algorithm’s potential to significantly improve inspection efficiency and adaptability in real-world scenarios.
The aim of long-term mine planning (LTMP) is two-fold: to maximize the net present value of profits (NPV) and determine how ores are sequentially processed over the lifetime. This scheduling task is computationally complex as it is rife with variables, constraints, periods, uncertainties, and unique operations. In this paper, we present trends in the literature in the recent decade. One trend is the shift from deterministic toward stochastic problems as they reflect real-world complexities. A complexity of growing concern is also in sustainable mine planning. Another trend is the shift from traditional operational research solutions — relying on exact or (meta) heuristic methods — toward hybrid methods. They are compared through the scope of the problem formulation and discussed via solution quality, efficiency, and gaps. We finally conclude with opportunities to incorporate artificial intelligence (AI)-based methods due to paucity, multiple operational uncertainties simultaneously, sustainability indicator quantification, and benchmark instances.
In this paper, we define X-convex and quasi-X-convex functions. This class of real functions is the generalization of a family of convex functions. Additionally, we provide a thorough analysis of the core characteristics of these functions in this paper, along with numerous examples that help to illustrate the ideas. Furthermore, quasi-X-convex, semistrictly quasi-X-convex, and strictly quasi-X-convex functions are used to study and show its applications on optimization problems.
The objective of this study is to numerically investigate and compare the characteristics of two distinct hybrid nanofluids EG-MoS2-SiO2 and H2O-Cu-Al2O3 flowing steadily over a channel created by two non-parallel absorbent porous walls. Further, the considered fluid flow is under the influence of exponential space-based heat source, viscous dissipation, Joule heating, radiation, and external magnetic field. The nonlinear partial differential equations and subjecting boundary conditions of the flow are transformed into a system of nonlinear ordinary differential equations through suitable similarity transformations and are solved by combining the shooting technique with the traditional Runge–Kutta method. The consequential results are produced utilizing MATLAB software. The comparisons of the velocity profiles, temperature profiles, surface drag, and Nusselt number for both hybrid nanofluids are illustrated as graphs. The findings indicate that H2O-Cu-Al2O3 exhibits better velocity profiles, EG-MoS2-SiO2 displays enhanced temperature profiles, while H2O-Cu-Al2O3 has improved skin friction and Nusselt number. It is noteworthy to mention that numerous industries, including manufacturing, power generation, chemical processes, microelectronics, and transportation, depend on improving heat transfer coefficients. Hence, the significance and novelty of this work lie in the evaluation of optimization and sensitivity analysis of the EG-MoS2-SiO2 hybrid nanofluid to enhance heat transmission using Response Surface Methodology.
Artificial intelligence (AI) and deep learning (DL) techniques are increasingly used in education because of advancements in online learning platforms and their ongoing implementation. The existing methods suffer from low-processing efficiency, high prediction error, and increased memory requirements when faced with vast learning and student behavior data. Thus, based on DL, this research suggests a way to analyze student behavior in e-learning. Data on student behavior are gathered, and a learning behavior model for online learning is created. The proposed optimal DL approach aims to screen the collected behavior data using data preparation, analysis, and statistics. Additionally, the Pearson correlation coefficient (PCC) approach is employed to determine the degree of data similarity. The novelty of the research is followed by utilizing an optimized DL network, known as a deep neural network with red deer optimization (ODNN-RDO), to mine students’ behavior data in e-learning programs. Two datasets, metrics including accuracy, precision, and recall, together with error measures like relative error, the root mean square error (RMSE), and absolute error, are utilized to test the created models. The improved generated models achieved 98.15% accuracy and 0–0.04% error compared to the current methods. The optimization procedure subsequently optimizes the components to acquire the best outcomes regarding faculty and parent performance monitoring of students. With effective monitoring, this model maximizes the e-learning platform for planning student growth.
Deep neural networks (DNNs) have witnessed widespread adoption across various domains. However, their computational demands pose significant challenges due to the extensive inter-neuron communication within the network. Moreover, the energy consumption of DNNs is substantial, primarily driven by the vast data movement and computational requirements. To overcome these challenges, novel accelerator architectures are essential. In this study, we present a novel heuristic algorithm for neuron grouping, catering to both fully connected and partially pruned DNN models. Our algorithm aims to minimize the overall data communication cost among neuron groups while also considering computational load balance. It outperforms existing heuristic neuron grouping methods classified into three main approaches from the literature by an average improvement in communication cost ranging from 33.01% to 47.11%. By optimizing neuron grouping, our approach may be used to enhance the efficiency of DNN accelerators, enabling improved performance and reduced energy consumption.
Machining of difficult-to-cut materials has always been a focus of research. In terms of surface roughness, it is one of the most important machinability indicators used to evaluate the performance of machining processes. This research aims to investigate the effect of biocompatible TiAlN-coated and uncoated carbide inserts, as well as the effect of cutting parameters such as feed, rotational speed, and depth of cut on surface roughness in the hard turning of M2 tool steel at 64 HRC. The central composite design is used to create the experimental layout. Surface roughness values are measured using separate experiments for coated and uncoated inserts. A quadratic model is selected, and an analysis of variance (ANOVA) is performed to test the adequacy of the developed model. From the ANOVA, it is found that feed and rotational speed are the most significant parameter while hard turning with TiAlN-coated and uncoated inserts, respectively. Cutting parameters are ranked according to their importance using the Pareto chart. The composite desirability function is employed to determine the optimal setting of cutting parameters to minimize the surface roughness and a confirmation experiment is conducted to validate the optimization results. Confirmation results are very close to the predicted value and the error between experimental and predicted results are 7.93% and 9.36% with TiAlN-coated and uncoated carbide inserts, respectively. TiAlN-coated carbide insert gives better surface roughness compared to an uncoated carbide insert.
This paper highlights the surface roughness optimization of a specific material, Al 3003, which has been subjected to the non-equal channel angular pressing (NECAP) process. Considering spindle speed, feed rate, and depth of cut as input variables and surface roughness as an output variable, experiments have been conducted based on the L27 orthogonal array of the Taguchi method. Four prediction models, namely exponential and response surface methodology (RSM) as mathematical models, and artificial neural networks (ANNs) prediction models with different training algorithms (Bayesian Regularization (BR) and Levenberg–Marquardt (LM)), are proposed. Applying effectiveness and performance criteria, the prediction accuracy of the exponential model (90.35%), RSM (93.07%), BR (97.83%), and LM (97.54%) shows that all proposed prediction models are efficient enough. The ANN model trained with BR is found to be the best fit for predicting surface roughness. In order to optimize surface roughness, a newly introduced optimization method called the Intelligible-in-time Logics Algorithm (ILA) is employed. High spindle speed (1000rev/min), low feed rate (100mm/min) and depth of cut (0.5mm) have been the optimum cutting parameter combinations to obtain minimum surface roughness (0.4956μm). The results have been verified by confirmation tests and Particle Swarm Optimization (PSO) method. ILA and PSO predict the same optimum parameter combinations and minimum surface roughness, while ILA performs optimization in less time (114.4s), about 3.5 times faster than PSO. The paper’s findings strongly advocate the application of ILA in machining data optimization.
The aim of this study is to highlight the importance of optimizing machining parameters to improve the performance and surface integrity of Inconel-825 superalloy using the Electrical Discharge Turning (EDT) process, an important configuration of Electrical Discharge Machining (EDM). The study uses a Face-Centered Central Composite Design (FCCCD) to conduct experiments and applies the Response Surface Methodology (RSM) and multi-objective genetic algorithm (MOGA) to optimize input parameters. Various factors like Gap Current (Ig), pulse on time (Ton), rotational speed (N), and Magnetic field assistance (B) are adjusted at different levels, while outcomes such as Material Removal Rate (MRR), Tool Wear Rate (TWR), Overcut (OC), and Surface Roughness (Ra) are measured. Analysis of Variance (ANOVA) is used to understand the impact of each input factor on the outcomes. The results demonstrate that both RSM and MOGA provide accurate predictions closely aligned with experimental results, with MOGA showing a slight advantage in predicting tool wear and surface roughness. Specifically, the RSM solution achieved a desirability of 0.693 with parameters Ig at 8 A, Ton at 48.082μs, speed at 1399.988RPM, and magnetic field at 0.3T, achieving MRR of 5.182mg/min, TWR of 3.138mg/min, OC of 166.716μm, and Ra of 2.047μm. The MOGA solution featured parameters Ig at 8.045 A, Ton at 48.557μs, speed at 1360.3 RPM, and magnetic field at 0.3T, yielding an MRR of 5.169mg/min, TWR of 2.983mg/min, OC of 170.037μm, and Ra of 2.060μm. SEM analysis confirmed improved surface quality under optimized conditions, while XRD analysis showed significant grain refinement and increased dislocation density.
The increasing demand for high-quality welds in various industries such as automotive, aerospace, and shipbuilding has led to the need for more efficient welding processes. Cold Metal Transfer (CMT) welding offers several advantages over traditional welding methods. This study investigates the CMT welding process applied to High-Strength Low-Alloy (HSLA) steel plates, focusing on optimizing weld parameters for enhanced joint quality and mechanical performance. The CMT process was selected for its ability to provide low heat input, thereby minimizing thermal distortion, and preserving the mechanical properties of the HSLA material. Key welding parameters, including welding speed (10–30mm/s), wire feed rate (2–4m/min), heat input (1.8–2.4kJ/mm), arc voltage (12–16V), and gas flow rate (3–5L/min), were systematically varied to assess their impact on weld integrity and strength. Uncertainty analysis is conducted and came out to be 3.25% which lies in an acceptable range. The AHP–TOPSIS analysis was conducted to identify the most important welding process parameters and equipment for achieving high-quality welds in CMT welding of steel. The results showed that welding speed, wire feed rate, and gas flow rate were the most important process parameters for achieving high-quality welds. In the AHP analysis, Tensile Strength achieved the highest priority (39%) while Impact Toughness (22%) followed it. After prioritizing the variables, an inter-relationship between the most favorable inputs with outputs is established using Artificial Intelligence (AI). Prediction analysis is performed to establish the most optimal welding setting among thousands of input sets. The sample with set 1 was found to be the best choice for producing high-quality welds in CMT welding of steel. The optimal parameter values were found to be a welding speed of 25mm/s, wire feed rate of 3m/min, arc voltage of 12V, gas flow rate of 5L/min, and heat input of 1.5kJ/mm yielding a tensile strength of 460MPa, hardness of 42HRC, impact toughness of 29 J, radiation of 110W/m2, convection of 90W/m2, and conduction of 150W/m2. This study provides valuable insights into the effective use of CMT for welding HSLA steel, offering practical guidelines for achieving high-quality welds in structural applications.
The growing need to machine challenging materials, especially nickel-based superalloys found in vital aerospace and automotive parts, is evident. This study examines the machining of 15.5 mm Nimonic-263 superalloy using Abrasive Waterjet Machining (AWJM). Nine trial sets, repeated thrice, are comprehensively evaluated using an L9 orthogonal array design to analyze crucial machining variables: the impact of Stand-off Distance, Waterjet Pressure, and Traverse Speed on Kerf Angle, Machining Time, and Material Removal Rate. Statistical significance is evaluated through multi-parametric analysis of variance, and quadratic multiple linear regression models are formulated to correlate output responses with machining variables. The JAYA optimization algorithm is introduced to optimize the machining process, aiming to minimize Kerf Angle and Machining Time while maximizing Material Removal Rate. A comparison with Ant-Lion, Genetic, and Multi-Verse Optimization algorithms highlights JAYA’s effectiveness. A confirmation test validates the JAYA algorithm’s output, confirming its superior performance. This research aids in optimizing machining parameters for challenging materials, benefiting critical components in various industries, especially aerospace.
Diffusion bonding of AA7075/AZ80 joint has been synthesized, studied and demonstrated to optimize the lap shear, Ram tensile and hardness properties. Response surface methodology (RSM) is applied to develop mathematical relationships between the control parameters of two factors and three-level responses. Optimization experiments were carried out to check the models’ adequacy. The results show a high degree of coincidence between the optimized and actual values, implying that the proposed models can accurately forecast lap shear, Ram tensile, and hardness properties force within the process parameter constraints of the diffusion bonding process. Scanned electron microscopic Scanning Electron Microscope (SEM) images, optical images, and radiography film photography investigations also revealed the excellent fracture resistance of the AA7075/AZ80 alloy, making it a suitable material for deployment in engineering applications.
GLARE is a type of laminate material made up of layers of aluminum and fiberglass used in automotive, and aircraft structures like fuselage panels, control surfaces, and wing skins due to their superior specific strength, fatigue, and damage tolerance. The inclusion of nanoclay filler was reported to improve the mechanical properties of the GLARE laminates. However, it is important to investigate the machinability of such laminates to extend their applicability in the industry. The current work optimizes the process parameters of the Abrasive Water Jet Machining (AWJM) process to cut the nanoclay-modified Fiber Metal Laminates (FMLs). The experiments were designed by following Taguchi’s L9 orthogonal array. The influence of factors like the velocity of waterjet, mass flow rate, and stand-off distance of the nozzle against the response such as cutting time and sub-surface delamination of layers were studied. The delamination was measured using the variation in thickness before and after the cutting process. The changes in the cutting surface were analyzed using macroscopic analysis. The study also developed the regression model and conducted ANOVA on generated data. Grey Relational Analysis (GRA) was used to identify the optimum values of input process parameters against multiple responses such as cutting time and delamination. The results revealed that the jet velocity significantly affected the cutting time, whereas the stand-off distance and mass flow rate affected the delamination thickness of the laminates. A slight plastic deformation was noted on the metal surfaces along with irregularities and fiber exposure was observed in the GFRP layers of laminates exhibited low cutting performance.
Aluminum metal matrix composites (AMMCs) are currently widely engaged in industrial sectors. No other monolithic material can match the characteristics of AMMCs. AMMCs are stronger than traditional materials and have a wide range of industrial uses. This research work aims to study the tribological properties of AA8079/Zirconium boride (ZrB2) composite manufactured via the stir casting (SC) process. The different combinations of composites are AA8079/0wt.% ZrB2, AA8079/5wt.% ZrB2, AA8079/10wt.% ZrB2, and AA8079/15wt.% ZrB2. The parameters are reinforcement wt.% [A], load [B], sliding velocity [C], and sliding distance [D]. When designing experiments using the Taguchi method, an L16 orthogonal array was used. In order to determine which process parameter had the biggest influence on the output variables, wear rate (WR), coefficient of friction (COF), and analysis of variance (ANOVA) were applied. Successful fabrication of different weight fractions of ZrB2 was synthesized with AA8079 matrix through the SC process. The microstructural investigations revealed the dispersion of ZrB2 particles over the surface of the base AA8079. The response table clearly depicts that the combinations of A and C are the more dominant factor for WR, while the combinations of B and C are the more interacting parameters for COF. From the ANOVA results, it is clear that A with a 55.26% contribution, is the most predominant parameter in attaining the least WR, and for COF, B with a 31.39% contribution, is the major influencing parameter.
In this investigation, Ti6Al4V was used as the base material for the shot peening process. Three major influencing parameters such as peening time, peening distance, and peening pressure were examined. The substrate was shot peened with stainless steel shot, with an average diameter of 0.6mm. The process parameters were optimized using the statistical tool Response Surface Methodology. A three-factor, five-level composite design matrix was employed to minimize the number of trial runs. The effect of shot peening parameters on hardness, surface roughness, and coefficient of friction was optimized. The adequacy of the model was checked using an analysis of variance. From the test results, it was observed that the peening performed with a shot peening time of 20s, a peening distance of 100mm, and a peening pressure of 3 bar resulted in a higher hardness of 433 VHN, a surface roughness of 5.8, and a coefficient of friction of 0.22. This may be attributed to the optimal residual compressive strength achieved through the shot peening process.
Sandwich composite materials with elastomeric cores and high-strength face layers have widespread applications in various engineering sectors as passive damping structural materials. This study examines the dynamic properties of sandwich plate with laminated composite face layers and smart magnetorheological elastomer (MRE) core under the action of the aerodynamic and hygrothermal loads. The dynamic model based on Kirchhoff’s plate theory is employed and the equations of motion are derived using Hamilton’s principle. The flow conditions are assumed supersonic and modeled by the first-order piston theory. The natural frequencies and aerodynamic pressure distributions are obtained from finite element model. Upon validating the model, the effects of various factors such as moisture, temperature and plate geometry on the critical aerodynamic pressure for different boundary conditions and magnetic fields are studied. Using these parametric data, a regression model is developed using Back-Propagation Neural Network to predict the critical aerodynamic pressure as a function of effective geometrical parameters. In order to enhance the aerodynamic stability, the critical aerodynamic pressure is maximized by the optimal selection of plate aspect ratio, face layer ply orientation sequence and core layer thickness ratio via the modified teaching–learning-based optimization (MTLBO) technique employing the trained neural network-based surrogate model. The approach is very convenient and it has been found that nondimensional aerodynamic pressure along with loss factor has improved almost twice. In the sensitivity analysis study, it is noticed that changes in aspect ratio around the optimal point have a relatively drastic effect on the critical aerodynamic pressure at all the face layer ply configurations.
Please login to be able to save your searches and receive alerts for new content matching your search criteria.