Application of fuzzy neural network to laser bending process of sheet metal

Abstract

The optimisation and selection of process plans is very important for laser bending of sheet metal to achieve the anticipated bending deformation. In this paper, an adaptive fuzzy neural network has been proposed to predict the bending deformation. This network integrates the learning power of neural networks with fuzzy inference systems. During the establishing process of the energy density (composed of three process parameters: laser power, scanning velocity, and spot diameter), width, thickness of sheet, and scanning path curvature were taken as four input variables of the network. The gradient descent learning algorithm was applied to optimally adjust the weight coefficients of the neural network and the parameters of the fuzzy membership functions. Then, the trained network was used to predict the laser bending deformation. Good correlation was found between the predictive and experimental results.     

Simulation and experiment of curve irradiated laser bending process of titanium alloy sheet

Abstract

Laser bending along a curve scanning path is a complex 3D forming process. To analyse the deformation behaviour of the process and the effect of process parameters on the bending angle of sheets, numerical simulation becomes indispensable. In this paper, non-linear transient heat transfer and dynamic structural computational models including thermal mechanical coupling analysis, in which the temperature dependence of the thermal and mechanical properties of the material are taken into account, have been developed. The temperature, stress, and strain fields as well as the effect of process parameters on the bending angle were calculated on the basis of models using the finite element method. Meanwhile, an experimental parameter investigation was also carried out. The results showed that, compared with the linear laser bending, curve irradiated laser bending has a significant reduction of the bending angle and the bending angle decreases with increasing path curvature. The bending angle increases with increasing laser power and decreasing spot diameter, and decreases roughly with decreasing scanning velocity. Good correlation was found between the numerically simulated results and the experimental data.     

TA2板料激光热应力弯曲成形 及其力学性能研究

用HVS-1000显微硬度测试仪、X-350A型X射线应力测定仪,以2.5 kW SM2000SM快轴流CO2激光器对0.6 mm厚的TA2板料进行扫描,按照正交试验理论安排成形工艺参数,研究了TA2板料弯曲成形时主要工艺参数对弯曲角度的影响,以及试样表面残余应力的分布和试样断面上的显微硬度变化。结果表明：正交试验中的4个工艺参数的作用是不同的,按其变化对弯曲变形量影响的大小排序,依次是扫描次数、光斑直径、激光束功率、扫描速度;成形参数对试样表面的残余应力分布也存在一定的影响;试样变形区断面上的显微硬度变化呈现出一定的规律。     

板料激光成形的正交实验设计与量纲分析

激光弯曲是一种利用激光加热来实现构件的柔性成形技术。利用正交实验研究各可控因素对弯曲角度的影响,通过量纲分析建立数学模型,根据正交实验数据对数学模型的相应参数进行回归求解。研究结果表明,利用正交实验可对激光成形的工艺参数进行全面评估;利用量纲分析法仿真复杂的激光弯曲过程是简便有效的。     

An ANFIS model for the prediction of flow stress of Ti600 alloy during hot deformation process

In this paper, an adaptive network-based fuzzy inference system (ANFIS) model has been established to predict the flow stress of Ti600 alloy during hot deformation process. This network integrates the fuzzy inference system with a back-propagation learning algorithm of neural network. The experimental results were obtained from Gleeble-1500 thermal-simulator at deformation temperatures of 800–1100 °C, strain rates of 0.001–10 s^?1, and height reduction of 70%. In establishing this ANFIS model, strain rate, deformation temperature and the strain are entered as input parameters while the flow stress are used as output parameter. After the training process, the fuzzy membership functions and the weight coefficient of the network can be optimized. A comparative evaluation of the predicted and the experimental results has shown that the ANFIS model used to predict the flow stress of Ti600 titanium alloy has a high accuracy and with absolute relative error is less than 17.39%. Moreover, the predicted accuracy of flow stress during hot deformation process of Ti600 titanium alloy using ANFIS model is higher than using traditional regression method, indicating that the ANFIS model was an easy and practical method to predict flow stress for Ti600 titanium alloy.     

Influence of beam polarisation in laser bending process

Abstract

In this paper, the influence of beam polarisation in the laser bending process was experimentally studied. Based on the laser beam polarisation, the laser absorption of the metallic specimen could be enhanced by increasing the incident angle. The bending angles are achieved in stainless foil specimens without absorptive coatings, and larger bending angles can be produced by single laser scanning with higher incident angles. Multipass laser bending experiments were also carried out on the same material with graphite coatings. The results show that the bending angle per pass is affected obviously by the beam polarisation at lower laser line energy; and the bending angle per pass increases significantly when the total bending angle is large enough. When using polarised light, the laser beam distortion and laser absorption change induced by the variation of the absorptive coatings and laser incident angle are the two main factors that affect the coupled laser energy. The bending rule is the synthesis effect of the two factors.     

A meshless method using the Takagi–Sugeno fuzzy model

This article proposes a new strong-form meshless method using the Takagi–Sugeno fuzzy model (MTSF) for solving differential equations (DEs). Considering the conventional fuzzy model, the fuzzy inference system (FIS) can be categorized into two architectures, a simple rule base using the Euclidean distance in a multidimensional space (Simple-FIS), and an adaptive neuro-fuzzy inference system (ANFIS). Accordingly, MTSF also can be implemented using Simple-FIS and ANFIS. Based on the two architectures, an approximation scheme for continuous functions is drawn out first. In turn, the derivation is further proposed in which the differential functions are approximated using two independent sets of points, one for the collocation point and the other for the rule point. Solving higher-order DEs becomes possible by following the derivations, and eventually numerical solutions can be obtained. Several examples of one-dimensional ordinary and two-dimensional partial DEs (ODEs and PDEs) are presented to demonstrate the performance of the MTSF method. By MTSF, solutions solved using Simple-FIS and using ANFIS are compared. Variations in boundary conditions and membership function parameters are also studied to examine the agreement among numerical solutions.     

Feasibility of underwater laser forming of laminated metal composites

Laminated metal composites are of great interest in various industries. Previous studies demonstrate undesired mechanical or microstructural changes in these composites during the laser forming process due to rapid temperature gradient. In this research, underwater laser forming is proposed to minimize this effect. This process could also be an effective method for on-site forming or repairing of large metal/composite sheets used in underwater applications, such as marine equipment, ships, and lake/sea-based offshore oil platforms. The underwater laser forming process is performed experimentally on a three-layered stainless steel/copper/stainless steel composite and compared with the results of in-air tests. Total forming time, bending rate, and microstructural changes are compared for both underwater and in-air conditions. The effects of forming parameters, such as the number of irradiations, laser beam velocity, diameter, and power, are also compared and discussed. It is shown that the bending angle per irradiation in underwater forming is significantly lower in comparison with in-air condition, but the production time is less due to the elimination of cooling time. Also, the microstructure of stainless steel at heat-affected zone was unchanged, and the hardness of upper layer experienced smaller changes when formed under water. The underwater laser forming process is demonstrated to be feasible and can be applied for underwater applications with a high degree of reliability.     

基于六边界优化角度函数的多道次辊弯成形研究

目的 为了提高多道次辊弯成形中板材的成形质量、减少板材纵向弯曲缺陷的产生,提出一种基于新型六边界成形角度分配函数的多道次辊弯成形优化方法。方法 根据翼缘端部水平面投影五次曲线推导出最优辊弯成形角度公式,结合COPRA研究板件峰值纵向应变,以确定最佳成形角度分配区间;在相同条件下,利用Abaquse模拟与实验研究不同成形角度对帽形件辊弯成形纵向弯曲缺陷的影响,并分析辊弯成形工艺参数对板材辊弯过程中应力-应变的影响。结果 新型六边界成形角度分配函数的多道次辊弯成形方法可有效改善板材纵向弯曲缺陷;应力随着成形角度增量的增加而增大,等效塑性应变随成形角度和成形角度增量的增加而增加;实验与模拟结果基本吻合,验证了模拟结果的正确性。结论 优化成形角度分配函数的多道次辊弯成形方法可有效改善板材纵向弯曲缺陷,为提高辊弯工艺精度与板材质量提供一定的理论指导。     

An analytical model for estimating deformation in laser forming

Laser forming of metal sheets offers the advantages of requiring no external forces and thus reduces cost and increases flexibility. This paper presents an analytical model to estimate the angle bent during the laser forming of a sheet. Plastic deformation is considered during both heating and cooling and is calculated based on a history-dependent incremental stress–strain relationship. On the basis of the proposed model with known temperature distributions, the bending angle induced by laser can be calculated. Comparison of the present model with experiment data is provided to demonstrate the accuracy of the present model under both TGM and BM.     

基于弯曲实验的DP980力学性能研究

目的 针对仅通过单向拉伸实验无法准确表征金属板材在弯曲成形过程中的力学性能变化的问题,研究通过弯曲实验获取材料力学性能参数.方法 对高强钢DP980展开力学性能测试研究,主要通过弯曲实验对材料弯曲变形过程中形成的弯矩曲率进行测试,将得到的弯矩曲率转化为应力-应变.分别将弯曲和拉伸得到的应力-应变数据导入到三点弯和辊弯成形有限元仿真中,预测板材的成形角度.结果 DP980弯曲变形时的屈服强度要大于轴向拉伸时的屈服强度;分别利用弯曲和拉伸实验测得的应力-应变数据进行仿真,与三点弯实验结果对比发现,采用弯曲实验得到的应力-应变数据对回弹量的预测偏大,而利用拉伸实验得到的应力-应变数据进行仿真,仿真得到的回弹量则偏小,弯曲实验下变形过程中的应变变化数据更加符合真实过程,与辊弯实验对比发现,利用弯曲实验数据进行仿真可以更准确地预测V形板的最终成形角度.结论 相较于单向拉伸实验,通过弯曲实验获取的材料力学性能参数可以更准确地描述材料在三点弯、辊弯成形过程中的力学性能变化.     

ANFIS based prediction and parametric analysis during turning operation of stainless steel 202

The paper deals with the parametric analysis and ANFIS-based modeling of process parameters during turning operation of stainless steel 202. In this experimental work, the Taguchi L16 DOE was utilized for designing the experiments considering three turning parameters namely feed rate, spindle speed as well as depth of cut. All the experiment was conducted at different parametric combinations and the performance namely material removal rate (MRR) and surface roughness (Ra) were evaluated. With the help of a suitable plot, the influences of process parameters on performance were analyzed. It was observed that depth of cutis is the majority influencing parameter for varying (parametric contribution is 53.33%) the MRR, whereas in case of surface roughness, the most contributing parameter is the spindle speed (parametric contribution is 95.71%). Further, the adaptive network-based fuzzy inference system (ANFIS) based modeling has been done to understand and establish the input-output relationship. The experimental results and ANFIS predicted results were compared and it is found that the ANFIS predicted results are accurate for predicting the responses during turning operation of stainless steel 202.     

Prediction of mechanical properties of a warm compacted molybdenum prealloy using artificial neural network and adaptive neuro-fuzzy models

Predictive models using artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) were successfully developed to predict yield strength and ultimate tensile strength of warm compacted 0.85 wt.% molybdenum prealloy samples. To construct these models, 48 different experimental data were gathered from the literature. A portion of the data set was randomly chosen to train both ANN with back propagation (BP) learning algorithm and ANFIS model with Gaussian membership function and the rest was implemented to verify the performance of the trained network against the unseen data. The generalization capability of the networks was also evaluated by applying new input data within the domain covered by the training pattern. To compare the obtained results, coefficient of determination (R²), root mean squared error (RMSE) and average absolute error (AAE) indexes were chosen and calculated for both of the models. The results showed that artificial neural network and adaptive neuro-fuzzy system were both potentially strong for prediction of the mechanical properties of warm compacted 0.85 wt.% molybdenum prealloy; however, the proposed ANFIS showed better performance than the ANN model. Also, the ANFIS model was subjected to a sensitivity analysis to find the significant inputs affecting mechanical properties of the samples.     

钣金V形折弯成形的回弹控制研究

为了实现对钣金V形折弯回弹的有效控制,在折弯加工过程中逐渐修正材料的性能参数,从而准确计算最终的折弯深度参数.本文对板料进行几次增量式的折弯加工,获取相应的成形及回弹角度参数,并通过理论模型修正材料的性能参数值,进而利用修正后的材料参数计算折弯深度参数.实验结果表明:修正后的材料性能参数接近拉伸实验的结果,折弯成形角度的偏差小于1°.增量式折弯方法避免了由材料参数误差引起的回弹控制误差,有效提高了V形折弯回弹的控制精度."     

Optimal neuro‐fuzzy control of hepatitis C virus integrated by genetic algorithm

Hepatitis C blood born virus is a major cause of liver disease that more than three per cent of people in the world is dealing with, and the spread of hepatitis C virus (HCV) infection in different populations is one of the most important issues in epidemiology. In the present study, a new intelligent controller is developed and tested to control the hepatitis C infection in the population which the authors refer to as an optimal adaptive neuro‐fuzzy controller. To design the controller, some data is required for training the employed adaptive neuro‐fuzzy inference system (ANFIS) which is selected by the genetic algorithm. Using this algorithm, the best control signal for each state condition is chosen in order to minimise an objective function. Then, the prepared data is utilised to build and train the Takagi–Sugeno fuzzy structure of the ANFIS and this structure is used as the controller. Simulation results show that there is a significant decrease in the number of acute‐infected individuals by employing the proposed control method in comparison with the case of no intervention. Moreover, the authors proposed method improves the value of the objective function by 19% compared with the ordinary optimal control methods used previously for HCV epidemic.Inspec keywords: epidemics, diseases, blood, medical computing, microorganisms, genetic algorithms, fuzzy control, neurocontrollers, adaptive control, medical control systemsOther keywords: genetic algorithm, hepatitis C blood born virus, liver disease, hepatitis C virus infection, epidemiology, intelligent controller, optimal adaptive neuro‐fuzzy controller, adaptive neuro‐fuzzy inference system, ANFIS, genetic algorithm, control signal, state condition, objective function minimisation, Takagi‐Sugeno fuzzy structure, acute‐infected individuals, ordinary optimal control methods, HCV epidemic     

基于数值模拟的管材平面弯曲成形几何加工精度规律

目的 建立高精度的有限元仿真模型可以有效地指导实际加工生产,在减少实验成本及结构件制造开发周期的同时提高成形效率。提高数值模拟中金属管材平面弯曲成形的几何加工精度,同时探究关键工艺参数对几何精度的影响规律,确定最佳工艺参数组合。方法 以管材平面弯曲成形构件为研究对象,建立了基于自由弯曲技术的管材弯曲成形有限元仿真模型,并通过实际加工实验验证了仿真精度,随后针对仿真模型的几何误差进行了参数补偿。将使用较高精度的仿真模型模拟得到的数据作为数据来源,研究关键工艺参数对仿真成形几何精度的影响机制,采用熵值法确定最佳工艺参数组合。结果 通过实际成形实验对比分析,在不同成形条件下,有限元仿真结果与实际加工结果高度吻合,两者之间的加工误差不超过2%,针对规格为32 mm×2 mm的20号碳钢管材,当轴向推进速度为5 mm/s,管材与弯曲模间隙值为0.25 mm时加工精度最高。结论 优化改进后的有限元仿真模型具有较高的几何成形精度,可有效指导实际成形工艺参数的优化工作。     

Influence of laser array performance on spectrally combined beam

Abstract

Incoherent spectral beam combining (SBC) of multiple laser beams is accomplished along the emitters’ arraying direction. Considering that the output beams from a laser array (LA) usually have deflection angles, positional displacements and divergence angles even after being collimated, a propagation model of SBC systems based on multilayer dielectric gratings has been built up. On the basis, properties of the spectrally combined beam affected by parameters of the LA have been discussed in detail. Simulation results show that with the increase in the deflection angle, both the power and the beam quality of the combined beam degrade dramatically. The positional displacement has little impact on the intensity distribution and the beam quality of combined beam but change the wavelength composition of the combined beam. The divergence angle strongly affects the intensity distribution and the beam quality of the combined beam. Additionally, the effect of the deflection angle on the output beam quality is more obvious and may shift the beam spot when comparing with that of the divergence angle.     

工艺参数对基于3D打印支撑模具板料双点渐进成形性能的影响

目的 提高基于3D打印支撑模具的板料双点渐进成形的成形性能,获得更好的成形参数。方法 选择工具头直径、加工步长、进给速度3个工艺参数为因素,设计单因素实验,加工支撑模具半径为45 mm的球冠,获得成形破裂角度,得到成形性能较好的工艺参数范围,确定成形性能较高的双点渐进成形方案。结果 通过实验数据对比并综合表面质量、加工时间及成形精度等因素考虑,最佳工艺参数工具头直径为 10 mm（实验选择8, 10, 12 mm）,垂直层进给量为0.5 mm（实验选择0.2, 0.5, 1 mm）,加工进给速度为 400 mm/min（实验选择300~500 mm/min）。结论 一定区域内工具头半径越小,垂直层进给量越大,工具头进给速度越大,板料成形性能越好。     

三辊楔横轧轧制空心轧件工艺参数对轧制力的影响规律

目的 研究分析5个工艺参数对轧制力的影响规律。方法 采用Deform软件建立三辊楔横轧轧制空轧件有限元模型,并对比模拟结果和实验检测结果中轧制力的变化规律,验证模拟结果的可靠性。利用正交实验法,全面系统分析各工艺参数对轧制力的影响规律。结果 轧制温度对轧制力的影响最大,其次是轧件轧后外径,然后是轧件内径,展宽角和成形角对轧制力的影响相对较小。结论 Deform软件模拟结果和实验中提取的轧制力曲线变化趋势基本一致,说明各工艺参数对轧制力的影响规律可靠。     

基于RF和ANFIS算法的直驱风电机组故障预警

针对风电机组运行工况复杂和单一状态参数不能较好实现故障早期预警的特点,提出随机森林算法(RF)和自适应模糊神经网络算法(ANFIS)相结合的故障预警方法。该方法充分考虑机组运行数据高维非线性特点,应用随机森林算法,建立有功功率与运行参数的数据驱动模型,计算各运行参数影响有功功率的相关度;构建自适应网络模糊推理系统模型,以训练误差最大值作为故障预警阈值,实时监测发电机运行状态。将该方法应用于某1.5 MW直驱机组发电机故障预警分析,结果表明,该方法能够提前预警发电机健康状态,避免严重事故发生,对风电场开展预防性维护、维修具有重要的指导意义。