Forming Force Prediction in Two Point Incremental Forming Using Backpropagation Neural Networks in Combination With Genetic Algorithms

Incremental Sheet Forming (ISF) process emerges as an alternative to classic shaping processes. Two variants of the IS process are used: negative forming or SPIF (Single Point Incremental Forming), in which it is not necessary using a die and positive forming or TPIF (Two Point Incremental Forming) ISF is usually performed on specifically designed machines controlled by CNC or in retrofitted CNC milling machines However, in the most of cases, the possibility of combining milling and ISF is not considered This paper is focused on a study about the implementation of ISF process in a CNC machining center through the specifi design of the clamping tools. So, it is not necessary to retrofit the machining center and it is possible to think abou combining both processes in multitask operations.

Amidst increasing governmental regulations and global initiatives to decarbonize manufacturing, there is a growing emphasis on environmentally sustainable, energy-efficient, and cost-effective production methods. Sheet-forming processes have made it possible to manufacture a variety of products we use and depend on in today’s globalized world, in the automotive, aerospace, medical, and food industries. Stamping or deep drawing are the preferred sheet-forming methods for mass-producing thin sheet parts due to its high production rate. However, the process involves high costs associated with the fabrication of specific dies for each part. Incremental sheet forming (ISF) has emerged as a promising technique and has gained widespread recognition as an alternative to traditional sheet forming. Researchers have studied ISF for the past decades, addressing and exploring alternatives to optimize the technique. Single-point incremental forming (SPIF) is one of the most popular ISF approaches because it can be accomplished using a CNC machine, a sheet clamp, and a small forming tool to make a wide variety of products of different shapes and materials. However, the technology’s cost-saving potential needs to be better understood, and predictive models must be improved to assess the process flows required to make parts using ISF. The cost prediction model presented in this work is intended to break down the cost dependencies of the ISF process to estimate a predetermined cost for each part before it is manufactured, considering material preparation, forming, and post-processing operations. A step forward in sheet forming research will be to provide a process-based cost model that can be flexible and adaptable to different types of machinery and tooling utilized. Cost calculations of a part made with ISF require knowledge of the systema as whole, such as forming process parameters, equipment characteristics, and forming geometry capabilities. The model relies on gathering process-based costs, including facilities, labor, equipment, materials, tools, consumables, and utilities, for all factors necessary to produce parts using ISF. The process-based cost model in this work involves an analytical bottom-up cost calculation methodology that is flexible and adaptable to various machine types. The ISF process is flexible, which means that the cycle time for different parts can vary by a considerable amount depending on the process parameters chosen (e.g., step down and feed rate) and the fixture and tools used. The aim of the present work is to lay the foundation for predicting the cost-effectiveness of products produced via the ISF process by considering the key processes involved. By gaining deeper insights into all costs involved in ISF and other innovative, environmentally friendly production methods, more sustainable manufacturing practices can be facilitated. These findings will contribute to global efforts to reduce carbon emissions, support responsible consumption and production, and benefit people, economy, and environment.

In this study, a back-propagation neural network (BPNN) model is developed to optimize forming parameters of aluminum alloy 5052-H32 sheets subjected to incremental sheet forming (ISF). Process parameters including tool diameter, step size in depth, tool feed rate, and tool spindle speed are varied to investigate the formability of the test, which is quantified by a multi-objective fitness function to reach the maximum forming angle and the minimum thickness reduction. A series of experimental tests have been conducted with different values of the above-mentioned process parameters. A BPNN model was then developed to predict material responses during ISF process. This BPNN model is employed to search for Pareto optimal solutions of formability of ISF. The derived Pareto optimal front appears to be a useful design guide for forming of aluminum alloy 5052 sheets in the ISF process.KeywordsIncremental sheet formingParameter optimizationBack-propagation neural networkMulti-objective optimalGenetic algorithm

Understanding a new wrinkling behavior of annular grooved panel during flexible free incremental sheet forming

Incremental sheet forming (ISF) is a versatile and innovative sheet metal forming technology which can readily produce asymmetrical, symmetrical, and complex geometric parts using a simple machine tool. However, limitations of the process include surface roughness, formability, and process throughput. Surface finish influences the quality, functionality, and aesthetics of the formed parts. Thus, ISF should be able to achieve an obligatory level of surface quality to be considered a competitive solution relative to other manufacturing processes. A variety of forming parameters have been investigated as primary causes of surface roughness variation in ISF. As a result, several forming parameters have been reported to be more influential to surface roughness than others. Further, surface roughness may differ based on a combination of parameter values while forming a workpiece rather than a single parameter alone. These influential forming parameters also have differing effects on surface roughness based on the workpiece material and the final part geometry. In addition, ISF can be divided into various categories, such as single-point incremental sheet forming (SPIF), two-point incremental sheet forming (TPIF) and multi-stage incremental sheet forming. The same set of forming parameters applied to these processes can yield a range of surface roughness values. Researchers have attempted different approaches to measure, analyze, and optimize the parameters that influence surface quality in ISF processes. However, the findings of these studies are sometimes contradictory. Most approaches consider a few forming parameters as variables in order to sort out the relationships between surface roughness and the selected forming parameters, while keeping other parameters constant. The forming parameters considered by prior research also vary from approach to approach, depending on researcher preferences and their perspective of influential ISF parameters on surface roughness. As the research of measuring, analyzing, and optimizing forming parameters to obtain desired surface quality is in the early stages of development, strong evidence on which researchers can agree is limited and lacks coherence. No prior reports summarizing the approaches used by researchers have been found in the literature, nor have comparative analyses been conducted to evaluate efficacy. A synthesis of the extant literature is provided herein to highlight the various approaches and practices that have been employed to study the effect of ISF process parameters on surface roughness. With the help of previous research findings, the outcomes reveal how various approaches compare and differ in terms of the identified influential forming parameters and offer potential directions for future study.

Preliminary modelling of forming forces in three directions for incremental sheet forming process based on the contact area

Incremental Sheet Forming (ISF) is a new-emerging sheet forming process well suited for small batch production or prototyping because it does not need any dedicated dies or punches. In this forming process, sheet metal parts are formed by a smooth-end tool in a stepwise way, during which plastic deformation is highly localized around the tool end. The part geometric accuracy obtained in the current ISF process, however, has not met the industry specification for precise part fabrication. This paper deals with a study on step depth, a critical parameter in ISF, for improving the geometric accuracy, surface quality and formability. Two sets of experiments were conducted to investigate the influence of step depth on part quality. Dimensional accuracy, surface morphology and material fracture of deformed parts were compared and analysed. An optimum value of step depth was suggested for forming a truncated cone. The present work provided significant fundamental information for the development of an advanced ISF control system on tool path control and optimization.

Incremental Sheet Forming (ISF) is a flexible and innovative rapid prototyping technique for the fabrication of limited sheet metal components. In the present investigation, the dependency of formability and thickness reduction of ISF parts on tool diameter, incremental step depth along with the preheating of sheet material has been determined. After preheating, initial grain size of the sheet material is selected as a parameter under study. Incremental Sheet Forming process has been studied using Taguchi design of experiments along with Response surface methodology (RSM). ANOVA, 3D surface graphs, S/N ratio and main effect plots have been analyzed. Results indicated that the initial grain size is the most significant parameter as far as forming load and thickness reduction is concerned in ISF. Preheating of the sheet material reduces forming load and favors homogenous thickness distribution. Response surface is optimized and a model developed can be used to predict forming load and thickness reduction within the limits of factors being studied.

The incremental sheet forming (ISF) process is a method of forming a metal sheet with a machine tool, such as a CNC or robot arm. In this study, the surface characteristics of the ISF process using the ball type tool and the conventional hemispherical tool were analyzed. Comparative experiments were conducted with the same size of the hemispherical tool and ball type tool. In experiments, the tool feed rate and spindle were fixed, and the step down was set up with seven levels. The surface profiles and roughness such as R<SUB>a</SUB> and R<SUB>z</SUB> after the ISF process with different values of the step down were compared. Additionally, the surface morphologies were analyzed through the scanning electron microscope. A ball type tool which can move and roll, can reduce the effect of friction effectively. As a result, the ISF process with a ball type tool can greatly reduce the damage of the surface of the product.

Incremental sheet forming (ISF) process is identified as a potential and economically viable process for sheet metal forming for the low volume production. The process is to prove a very flexible and can be carried out on a computer numerical control (CNC) milling machine, robots, or on machines which are specially designed for ISF applications. In present work, the effort has been made to investigate the behavior of Extra Deep Drawing (EDD) steel in ISF process. The state of stresses and strains in incremental forming of VWACF and VWAPF parts have been studied through finite element simulations. The thickness distribution of these parts has been measured experimentally and compared with the results of finite element simulations (FES) using Ansys software. The changes in microstructure and microhardness are being detected due to incremental deformations which have also been studied through optical microscopic analysis and micro-Vickers hardness tester. It has been again verified by performing the experiments.

This paper presents the numerical prediction of fracture depth in the part formed with the incremental sheet forming (ISF) process. The plastic deformation behaviour during forming is modelled through Johnson–Cook plasticity model and fracture is simulated through the constant equivalent plastic strain criteria. Finite element analysis has been used for the numerical investigation of the effectiveness of the present material model. The results from simulations are validated through physical experiments on a three-axis machining centre. Two truncated cones of different wall angles with 0.91-mm-thick sheets of Al1050 H14 material were formed by ISF process. The results delineate a new perspective on present material model with respect to ISF and offer an accurate FEA model for carrying simulations of ISF process.

Mass production is a fundamental requirement across various industries such as automotive, medical (e.g., artificial limbs), aerospace, and household appliances. Traditionally, this has been achieved through conventional metal forming processes like press work. However, for batch production scenarios, advanced and flexible manufacturing techniques such as Incremental Sheet Forming (ISF) are more suitable, as they can significantly reduce production costs. To optimize the ISF process, it is essential to study key process parameters, including step size, tool size, feed rate, spindle speed, and wall angle, as these factors directly influence formability and the deformation behavior particularly when working with Ultra High Molecular Weight Polyethylene (UHMWPE), which shows great potential in medical applications. This study aims to investigate critical aspects of the ISF process on UHMWPE, such as the forming limit diagram. It also involves a comparative analysis between experimental and analytical results using Finite Element Method (FEM), focusing major and minor strain values, and forming forces.

Incremental Sheet Forming (ISF) has great potential to form complex sheet metal parts without using component specific tooling. Formability in ISF process is higher than the conventional forming processes but achieving good geometrical accuracy is a challenging task. Anisotropy of material causes variation of thickness with respect to rolling direction, which effects stiffness, spring-back and accuracy. Variation of thickness and spring-back with rolling direction is studied using experimental and numerical analysis for a conical geometry formed using extra deep drawing steel having high anisotropy. Comparison of anisotropy and isotropy is done using numerical analysis. Results showed that, thickness is low in the direction with low ratio of width to thickness strain (r-value), resulting in higher spring-back. This directional property has to be considered in tool path design to enhance the accuracy. When material is assumed to be isotropic, variation of thickness and spring-back with respect to direction is insignificant.

Human resource management risks are due to the failure of employer organization to use relevant human resources reasonably and can result in tangible or intangible waste of human resources and even risks; therefore, constructing a practical early warning model of human resource management risk is extremely important for early risk prediction. The back propagation (BP) neural network is an information analysis and processing system formed by using the error back propagation algorithm to simulate the neural function and structure of the human brain, which can handle complex and changeable things that do not have an obvious linear relationship between output results and input factors, so as to find the objective connection between the two. Based on the summary and analysis of previous research works, this article expounded the research status and significance of early warning for human resource management risks, elaborated the development background, current status, and future challenges of the BP neural network, introduced the method and principle of the BP neural network’s connection weight calculation and learning training, performed the risk inducement analysis, index system establishment, and network node selection of human resource management, constructed an early warning model of human resource management risk based on the BP neural network, conducted the risk warning model training and detection based on the BP neural network, and finally carried out a simulation and its result analysis. The study results show that the early warning model of human resource management risk based on the BP network is effective, and this trained and tested BP network risk warning model can be used to conduct early warning empirical research on human resource risks to prevent human resource risks, ensure enterprise’s benign operation, and at the same time play a role in supervision and promotion of market order rectification.

This work addresses through bibliographies and experiments the behavior of sheet brass 70/30 for Incremental Sheet Forming process - ISF, based on the parameters: wall angle (), step vertical (ΔZ) strategy and the way the tool. Experiments based on the method called Single Point Incremental Forming - SPIF. For execution of practical tests, we used the resources: software CAD / CAM, CNC machining center with three axles, matrix incremental, incremental forming tool and a device press sheets. Furthermore, measurement was made of the true deformation () and thickness (s1). Practical tests have shown that the spiral machining strategy yielded a greater wall angle, compared to the conventional strategy outline.