Application of the Conjugate Gradient Optimization Algorithm of Neural Network on Laser Machining

在应用激光技术加工复杂曲面时,通常以采样点集为插值点来建立曲面函数,然后实现曲面上任意坐标点的精确定位。人工神经网络的BP算法能实现函数插值,但计算精度偏低,往往达不到插值精确要求,造成较大的加工误差。提出人工神经网络的共轭梯度最优化插值新算法,并通过实例仿真,证明了这种曲面精确定位方法的可行性,从而为激光加工的三维精确定位提供了一种良好解决方案。这种方法已经应用在实际中。

Effect of Nb Content on the Microstructure and Mechanical Properties of Zr-Cu-Ni-Al-Nb Glass Forming Alloys

(Zr65Al10Ni10Cu15)(100-x) Nb-x glass forming alloys with Nb contents ranging from 0 to 15 at.% were prepared by water-cooled copper mould cast. The alloys with different Nb contents exhibited different microstructures and mechanical properties. Unlike the monolithic Zr65Al10Ni10Cu15 bulk metallic glass, only a few primary bee beta-Ti phase dendrites were found to distribute in the glassy matrix of the alloys with x = 5. For alloys with x = 10, more beta-phase dendrites forms, together with quasicrystalline particles densely distributed in the matrix of the alloys. For alloys with x = 15, the microstructure of the alloy is dominated by a high density of fully developed P-phase dendrites and the volume fraction of quasicrystalline particles significantly decreases. Room temperature compression tests showed that the alloys with x = 5 failed at 1793 MPa and exhibited an obvious plastic strain of 3.05%, while the other samples all failed in a brittle manner. The ultimate fracture strengths are 1793, 1975 and 1572 MPa for the alloys with x = 0, 10 and 15 at.% Nb, respectively.

人工神经网络技术在板料激光弯曲中的应用

基于人工神经网络基本理论,建立在板料激光弯曲中预测材料表面最高温度、弯曲角度的BP网络模型.借助于MATLAB仿真软件中的神经网络工具箱作为开发平台,将试验样本数据和经过试验验证的数值计算结果作为补充的样本数据用于BP网络的训练,利用训练好的BP网络对非线性的样本数据规律进行拟合,实现激光加工工艺参数的优化,为实际生产和加工提供有效的依据.

Magnetic field design for floating zone crystal growth

The magnetic fields produced by electrical coils are designed for P-doped Si crystal growth in a floating full zone in microgravity environment. The fields are designed specially to reduce the how near the free surface and then in the melt zone by adjusting the coil positions near the melt zone. The effects of the designed magnetic fields on reducing the Row velocity and the non-uniformity of the concentration distribution in the melt zone are better than those of the case of a uniform longitudinal magnetic field, obtained by numerical simulation. It is expected to improve the radial macro-segregation and reduce the convection in the crystal growth at the same time by using the designed magnetic field.

Torsional impact of transversely isotropic solid with functionally graded shear moduli and a penny-shaped crack

The torsional impact response of a penny-shaped crack in an unbounded transversely isotropic solid is considered. The shear moduli are assumed to be functionally graded such that the mathematics is tractable. Laplace transform and Hankel transform are used to reduce the problem to solving a Fredholm integral equation. The crack tip stress fields are obtained. Investigated are the influence of material nonhomogeneity and orthotropy on the dynamic stress intensity factor. The peak value of the dynamic stress intensity factor can be suppressed by increasing the shear moduli's gradient and/or increasing the shear modulus in a direction perpendicular to the crack surface.

Air flow over a mountain and the convective boundary-layer

In this paper, the analytical model coupling the convective boundary layer (CBL) with the free atmosphere developed by Qi and Fu (1992) is improved. And by this improved model, the interaction between airflow over a mountain and the CBL is further discussed. The conclusions demonstrate: (1) The perturbation potential temperatures in the free atmosphere can counteract the effect of orographic thermal forcing through entraining and mixing in the CBL. If u(M)BAR > u(F)BAR, the feedback of the perturbation potential temperatures in the free atmosphere is more important than orographic thermal forcing, which promotes the effect of interfacial waves. If u(M)BAR < u(F)BAR, orographic thermal forcing is more important, which makes the interfacial height and the topographic height identical in phase, and the horizontal speeds are a maximum at the top of the mountain. (2) The internal gravity waves propagating vertically in the free atmosphere cause a strong downslope wind to become established above the lee slope in the CBL and result in the hydraulic jump at the top of the CBL. (3) With the CBL deepening, the interfacial gravity waves induced by the potential temperature jump at the top of the CBL cause the airflow in the CBL to be subcritical.

Magnetic properties of sintered sm2fe17ny magnets

Sintered magnets of Sm2Fe17Ny nitrides, with a density of 6.0-7.4 g/cm3, have been prepared by using an explosion technique. Both crystalline structure and the magnetic properties of Sm2Fe17Ny nitrides were retained in the process. The sintered magnet had a remanence B(r)=0.83 T, an intrinsic coercivity mu(0i)H(c)=0.57 T and an energy product (BH)max=88 kJ/m3. The temperature dependence of coercivity and remanence were also measured. The temperature coefficients alpha of remanence and beta of coercivity are -0.076%/degrees-C and -0.51%/degrees-C, respectively.

Diffusion sliding rate in the binary gaseous mixture

radiation incident upon a test cell filled with gaseous SF6 has

基于人工神经网络的油水旋流分离器分离性能预测

采用改进的BP神经网络模型模拟水力旋流器的油水分离过程.根据水力旋流器的实际运行条件,确定旋流器模型设计中的优化神经网络结构,将遗传算法用于优化三层BP神经网络的初始权重,采用PRP共轭梯度法优化BP算法.结果表明,采用人工神经网络模型预测油水分离水力旋流器的分离性能是切实可行的,它能成功地模拟旋流器的分离过程,进而实现旋流器操作控制的优化.

利用改进的神经网络预测腐蚀管道的剩余强度

将BP神经网络和遗传算法相结合 ,得到一种新的神经网络 ,并将这种神经网络成功用于计算腐蚀管道的剩余强度和最大允许输送压力。通过示例分析 ,得到下面结论 :不同计算方法计算得到的剩余强度和最大允许输送压力相差较大 ,Wes - 2 80 5 - 97规范、ASME -B31G规范、CVDA— 84规范等都比J积分方法计算得到的剩余强度和最大允许输送压力偏大 ;DM断裂力学方法计算得到的剩余强度和最大允许输送压力比J积分偏小 ;J积分方法和基于J积分方法的改进的遗传神经网络方法计算结果比较接近 ,可以认为是计算剩余强度和最大允许输送压力较好的方法

人工神经网络技术在成形模具表面激光强化中的应用

基于人工神经网络基本理论，建立在成形模具表面激光强化中预测材料表面最高温度、强化效果的BP网络模型。借助于MATLAB仿真软件中的神经网络工具箱作为开发平台，将试验样本数据和经过试验验证的数值计算结果作为补充的样本数据用于BP网络的训练，利用训练好的BP网络对非线性的样本数据规律进行拟合，实现激光加工工艺参数的优化，为实际生产和加工提供有效的依据。

预测腐蚀管道剩余强度的新方法

将BP神经网络和遗传算法相结合 ,得到了一种可计算腐蚀管道剩余强度和最大允许注水压力的新神经网络。通过实例分析 ,将 7种常用规范和改进的遗传神经网络方法进行了比较。结果表明 ,不同计算方法得到的剩余强度和最大允许注水压力相差较大 ,Wes 2 80 5 - 97规范、ASMEB31G规范、CVDA— 84规范、Irwin断裂力学方法等都比J积分方法的剩余强度和最大允许注水压力偏大 ;Burdiken和DM断裂力学方法计算得到的剩余强度和最大允许注水压力比J积分偏小 ;J积分方法和基于J积分方法的改进遗传神经网络方法计算结果比较接近 ,比较适中 ,可以认为是计算管道剩余强度和最大允许注水压力较好的方法

腐蚀管道的剩余强度计算方法研究

对目前国内外常用规范进行归纳和总结,得到5种常用方法: ASME—B31G,DM方法,Wes-2805—97,CVDA-84和J积分方法.本文将BP神经网络和遗传算法相结合,得到一种新的神经网络,并将这种神经网络成功用于计算腐蚀管道的剩余强度和最大允许注水压力.通过示例分析,对7种常用规范和本文提出的改进的遗传神经网络方法进行了比较,得到下面结论:不同计算方法计算得到的剩余强度和最大允许注水压力相差较大, Wes-2805-97规范、 ASME—B31G规范、 CVDA-84规范等都比J积分方法计算得到的剩余强度和最大允许注水压力偏大、偏保守; DM断裂力学方法计算得到的剩余强度和最大允许注水压力比J积分偏小、偏危险; J积分方法和基于J积分方法的改进的遗传神经网络方法计算结果比较接近,比较适中,可以认为是计算剩余强度和最大允许注水压力较好的方法.

Analytical Methods of Residual Strength in Injecting Water Pipeline

In this paper, common criterions about residual strength evaluation at home and abroad are generalized and seven methods are acquired, namely ASME-B31G, DM, Wes-2805-97, CVDA-84, Burdekin, Irwin and J integral methods. BP neural network are Combined with Genetic Algorithm (GA) named by modified BP-GA methods to successfully predict residual strength and critical pressure of injecting water, corrosion pipelines. Examples are shown that calculation results of every kind of method have great difference and calculating values of Wes-2805-97 criterion, ASME-B31G criterion, CVDA-84 criterion and Irwin fracture mechanics model are conservative and higher than, those of J integral methods while calculating values of Burdiken model and DM fracture mechanics model are dangerous and less than those of J integral methods and calculating values of modified BP-GA methods are close and moderate to those of J integral methods. Therefore modified BP-GA methods and J integral methods are considered better methods to calculate residual strength and critical pressure of injecting water corrosion pipelines

Quantum computation based on a quantum switch in cavity QED

A feasible scheme for constructing quantum logic gates is proposed on the basis of quantum switches in cavity QED. It is shown that the light field which is fed into the cavity due to the passage of an atom in a certain state can be used to manipulate the conditioned quantum logical gate. In our scheme, the quantum information is encoded in the states of Rydberg atoms and the cavity mode is not used as logical qubits or as a communicating "bus"; thus, the effect of atomic spontaneous emission can be neglected and the strict requirements for the cavity can be relaxed.