NURBS CURVE INTERPOLATOR WITH ADAPTIVE ACCELERATION-DECELERATION CONTROL

The feedrate profile of non-uniform rational B-spline （NURBS） interpolation due to the contour errors is analyzed. A NURBS curve interpolator with adaptive acceleration-deceleration control is presented. In interpo- lation preprocessing, the sensitive zones of feedrate variations are processed with acceleration-deceleration control. By using the proposed algorithm, the machining accuracy is guaranteed and the feedrate is adaptively adjusted to he smoothed. The mechanical shock imposed in the servo system is avoided by the first and the second time derivatives of feedrates. A simulation of NURBS interpolation is given to demonstrate the validity and the effectiveness of the algorithm. The proposed interpolator can also be applied to the trajectory planning of the other parametric curves.

Research on cubic polynomial acceleration and deceleration control model for high speed NC machining

To satisfy the need of high speed NC (numerical control) machining, an acceleration and deceleration (acc/dec) control model is proposed, and the speed curve is also constructed by the cubic polynomial. The proposed control model provides continuity of acceleration, which avoids the intense vibration in high speed NC machining. Based on the discrete characteristic of the data sampling interpolation, the acc/dec control discrete mathematical model is also set up and the discrete expression of the theoretical deceleration length is obtained furthermore. Aiming at the question of hardly predetermining the deceleration point in acc/dec control before interpolation, the adaptive acc/dec control algorithm is deduced from the expressions of the theoretical deceleration length. The experimental result proves that the acc/dec control model has the characteristic of easy implementation, stable movement and low impact. The model has been applied in multi-axes high speed micro fabrication machining successfully.

APPLICATION OF INTEGER CODING ACCELERATING GENETIC ALGORITHM IN RECTANGULAR CUTTING STOCK PROBLEM

An improved genetic algorithm and its application to resolve cutting stock problem arc presented. It is common to apply simple genetic algorithm （SGA） to cutting stock problem, but the huge amount of computing of SGA is a serious problem in practical application. Accelerating genetic algorithm （AGA） based on integer coding and AGA＇s detailed steps are developed to reduce the amount of computation, and a new kind of rectangular parts blank layout algorithm is designed for rectangular cutting stock problem. SGA is adopted to produce individuals within given evolution process, and the variation interval of these individuals is taken as initial domain of the next optimization process, thus shrinks searching range intensively and accelerates the evaluation process of SGA. To enhance the diversity of population and to avoid the algorithm stagnates at local optimization result, fixed number of individuals are produced randomly and replace the same number of parents in every evaluation process. According to the computational experiment, it is observed that this improved GA converges much sooner than SGA, and is able to get the balance of good result and high efficiency in the process of optimization for rectangular cutting stock problem.

A new accelerating algorithm for multi-agent reinforcement learning

In multi-agent systems, joint-action must be employed to achieve cooperation because the evaluation of the behavior of an agent often depends on the other agents’ behaviors. However, joint-action reinforcement learning algorithms suffer the slow convergence rate because of the enormous learning space produced by joint-action. In this article, a prediction-based reinforcement learning algorithm is presented for multi-agent cooperation tasks, which demands all agents to learn predicting the probabilities of actions that other agents may execute. A multi-robot cooperation experiment is run to test the efficacy of the new algorithm, and the experiment results show that the new algorithm can achieve the cooperation policy much faster than the primitive reinforcement learning algorithm.

The application of projection pursuit classification in the process of strategy selection and evaluation based on the real coded accelerating genetic algorithm

During the process of enterprises＇ strategy evaluation and selection, there are many evaluating indicators, and among them there are some potential correlations and conflicts. Thus it poses the problems to the decision-makers how to conduct correct evaluation on a business and how to make strategy adjustment and selection according to the evaluation. Based on the qualitative and quantitative method, the paper introduces the Projection Pursuit Classification （PPC） model based on the Real-coded Accelerating Genetic Algorithm （RAGA） into the process of enterprises＇ strategy evaluation and selection. The characteristic of PPC model is that it ultimately overcomes the influence of the proportion of subjectivity and avoids precocious convergence, thus providing a new objective method for strategy evaluation and selection by pursuing the most objective strategy evaluation to make the relatively sensible strategy portfolio and action.

Design of S-band photoinjector with high bunch charge and low emittance based on multi-objective genetic algorithm

High-brightness electron beams are required to drive LINAC-based free-electron lasers(FELs)and storage-ring-based synchrotron radiation light sources.The bunch charge and RMS bunch length at the exit of the LINAC play a crucial role in the peak current;the minimum transverse emittance is mainly determined by the injector of the LINAC.Thus,a photoin-jector with a high bunch charge and low emittance that can simultaneously provide high-quality beams for 4th generation synchrotron radiation sources and FELs is desirable.The design of a 1.6-cell S-band 2998-MHz RF gun and beam dynamics optimization of a relevant beamline are presented in this paper.Beam dynamics simulations were performed by combining ASTRA and the multi-objective genetic algorithm NSGA II.The effects of the laser pulse shape,half-cell length of the RF gun,and RF parameters on the output beam quality were analyzed and compared.The normalized transverse emittance was optimized to be as low as 0.65 and 0.92 mm·mrad when the bunch charge was as high as 1 and 2 nC,respectively.Finally,the beam stability properties of the photoinjector,considering misalignment and RF jitter,were simulated and analyzed.

Design and Optimization of Winograd Convolution on Array Accelerator

With the rapid development and popularization of artificial intelligence technology,convolutional neural network(CNN)is applied in many fields,and begins to replace most traditional algorithms and gradually deploys to terminal devices.However,the huge data movement and computational complexity of CNN bring huge power consumption and performance challenges to the hardware,which hinders the application of CNN in embedded devices such as smartphones and smart cars.This paper implements a convolutional neural network accelerator based on Winograd convolution algorithm on field-programmable gate array(FPGA).Firstly,a convolution kernel decomposition method for Winograd convolution is proposed.The convolution kernel larger than 3×3 is divided into multiple 3×3 convolution kernels for convolution operation,and the unsynchronized long convolution operation is processed.Then,we design Winograd convolution array and use configurable multiplier to flexibly realize multiplication for data with different accuracy.Experimental results on VGG16 and AlexNet network show that our accelerator has the most energy efficient and 101 times that of the CPU,5.8 times that of the GPU.At the same time,it has higher energy efficiency than other convolutional neural network accelerators.

Hybrid Global Optimization Algorithm for Feature Selection

This paper proposes Parallelized Linear Time-Variant Acceleration Coefficients and Inertial Weight of Particle Swarm Optimization algorithm(PLTVACIW-PSO).Its designed has introduced the benefits of Parallel computing into the combined power of TVAC(Time-Variant Acceleration Coefficients)and IW(Inertial Weight).Proposed algorithm has been tested against linear,non-linear,traditional,andmultiswarmbased optimization algorithms.An experimental study is performed in two stages to assess the proposed PLTVACIW-PSO.Phase I uses 12 recognized Standard Benchmarks methods to evaluate the comparative performance of the proposed PLTVACIWPSO vs.IW based Particle Swarm Optimization(PSO)algorithms,TVAC based PSO algorithms,traditional PSO,Genetic algorithms(GA),Differential evolution(DE),and,finally,Flower Pollination(FP)algorithms.In phase II,the proposed PLTVACIW-PSO uses the same 12 known Benchmark functions to test its performance against the BAT(BA)and Multi-Swarm BAT algorithms.In phase III,the proposed PLTVACIW-PSO is employed to augment the feature selection problem formedical datasets.This experimental study shows that the planned PLTVACIW-PSO outpaces the performances of other comparable algorithms.Outcomes from the experiments shows that the PLTVACIW-PSO is capable of outlining a feature subset that is capable of enhancing the classification efficiency and gives the minimal subset of the core features.

求解非线性方程组的非单调自适应加速Levenberg-Marquardt算法

提出一种新的求解非线性方程组的非单调自适应加速Levenberg-Marquardt算法,该算法使用一种新的自适应函数更新Levenberg-Marquardt参数,这种Levenberg-Marquardt参数的更新方式可提高过于成功的迭代中模型与目标函数的一致性,从而加快算法的收敛速度.数值实验结果表明,该算法具有良好的数值计算性能.

分支定界搜索信息深度引导的电-气互联系统调度决策加速求解方法

电-气互联系统调度决策问题旨在实现天然气系统和电力系统中可调节资源的最佳配置,其精准性与高效性直接影响电-气互联系统运行的安全性与经济性。为描述可调节资源离散状态、非线性运行特性等物理性质,电-气互联系统调度决策问题中含有规模庞大的离散决策变量,模型复杂度高,使得现有依赖于商业混合整数线性规划(MILP)求解器的电力系统运筹优化技术面临“组合爆炸”的计算负担。为此,该文提出一种分支定界搜索信息深度引导的电-气互联系统调度决策加速求解方法。所提方法利用分支定界初始搜索阶段的信息构建小规模辅助MILP模型,并内嵌于分支定界搜索过程,引导剪除更多冗余搜索空间,在不损失最优性的前提下加速收敛。基于RTS-GMLC电力系统和天然气系统不同负荷水平及线性分段数下的30个算例仿真结果说明,相比于直接使用商业MILP求解器,所提方法在不损失最优性的前提下可实现平均4.20倍的加速,验证了所提方法的有效性。

一种基于函数逼近的柔性加减速算法研究

嵌入式数控系统优点诸多,但系统资源、处理能力有限。三角函数加减速算法拥有柔性冲击小、精度高的优点,但其计算复杂,当运用在嵌入式数控系统时,难以满足系统的高实时性要求。针对这个问题,提出一种加减速算法,基于最佳平方逼近方法,利用多项式函数逼近三角函数,进而推理、构建出完整的加减速方程,随后分析算法在不同情况下的速度规划。最终对该算法进行了仿真分析并在以MCU为控制器的数控平台进行了实验,结果表明:算法在保留三角函数曲线柔性的同时降低了计算复杂度,提高了加工效率。

基于代理遗传优化的智能驾驶系统加速测试方法

提出了一种基于代理遗传优化的智能驾驶系统加速测试方法。首先,通过场景要素层次分析权值与优解区域特征改进参数采样模块中的拉丁超立方采样区间,实现了采样效率与优化效果的协同提升;其次,利用参数采样结果和重复度筛选机制增加遗传寻优模块的种群多样性,克服了传统遗传算法的局部收敛难题;然后,利用基于循环更新机制的代理筛选模块对场景测试结果进行预测,平衡了加速算法与代理模型应用之间的效率与精度矛盾;最后,搭建仿真平台在高维时序分解的前车变速场景下对待测智能驾驶系统进行加速测试与验证。结果表明,本文提出的方法可有效搜寻大量关键场景并提升测试效率。

基于WOA-ELM的空间分层结构FBG三维振动加速度传感器非线性解耦

针对三维振动加速度传感器存在的维间耦合干扰问题,以空间分层结构光纤布拉格光栅(FBG)三维振动加速度传感器为研究对象,阐述了三维振动加速度传感的基本原理。其次,构建了振动加速度动态标定实验平台,并分析了传感器的结构耦合特性。最后,提出一种基于鲸鱼算法优化极限学习机(WOA-ELM)的神经网络模型并进行了非线性解耦实验,其结果显示,在x、y、z三轴的平均测量误差分别降至1.58%、1.17%、0.95%,平均I类和II类误差最大值分别降至0.73%和0.37%。为验证解耦效果,将WOA-ELM与其他算法等进行解耦效果对比。结果表明,WOA-ELM更有效地降低三维振动加速度传感器的维间耦合干扰,提高测量精度。

门槛阈值自匹配的车载呼救系统设计

为了提高车辆碰撞自动呼救系统(Automatic Crash Notification System,ACNS)的抗干扰能力和事故信息的准确性,提出了一种具有自适应门槛阈值的ACNS触发算法。基于门槛阈值与路面国际平整度指数之间的关联模型,设计ACNS触发算法,并实现ACNS门槛阈值随路面状况和车速的动态匹配;基于STM32F103ZET6微控制器,利用加速度信号采集模块、定位模块和通信模块等模块设计一种车辆事故自动呼救系统终端;利用道路实车试验和触发测试试验测试系统性能;结果表明:ACNS终端能够实现门槛阈值根据不同路面状况的动态匹配,并对相关信息进行实时处理及发送呼救信息。

高质量加工五次多项式速度规划算法研究

通过分析直线、指数、S曲线以及正弦函数几种常用的加减速算法,针对传统的速度规划算法存在的加工曲线不连续以及加工过程出现振荡、加工精度低等问题,提出适用于高质量加工的五次多项式速度规划算法,将整个加工过程分段,细化每一段的方程,并介绍对于待定的NURBS曲线使用五次多项式速度规划算法进行插补的过程,针对快速插补和实时插补两个阶段进行优化。结尾根据仿真加工实验图像得出结论,该算法实现了加工过程中运动曲线的连续变化、柔性变化。并将加工精度控制在理想范围之内,适应于高质量的加工。

数字乡村建设对防返贫能力的影响及空间效应研究

防止规模性返贫是扎实推进乡村振兴的关键所在,数字乡村建设对提升农村防返贫能力具有重要意义。本文基于2016~2022年中国30个省(区、市)的面板数据,运用基于加速遗传算法的投影寻踪模型测度数字乡村建设水平与防返贫能力,通过核密度估计刻画两者的时空分异特征,利用空间杜宾模型深入分析数字乡村建设对防返贫能力的空间溢出效应。研究发现:2016~2022年,数字乡村建设水平与防返贫能力整体上在不断提高,数字乡村建设存在多极化趋势,防返贫能力两极化现象逐渐减弱。农村防返贫能力具有显著的空间聚集特征,主要表现为“高—高”和“低—低”聚集模式。空间杜宾溢出效应分解表明:数字乡村建设对防返贫有着显著的正向影响以及正的空间溢出效应。据此,对未来建设数字乡村提出相关建议,并探索出提升防返贫能力的新路径,未来可尝试从溢出边界进一步探索空间溢出效应。

演化算法的DQN网络参数优化方法

为了解决DQN(Deep Q Network)在早期会出现盲目搜索、勘探利用不均并导致整个算法收敛过慢的问题,从探索前期有利于算法训练的有效信息获取与利用的角度出发,以差分演化(Differential Evolution)算法为例,提出了一种基于演化算法优化DQN网络参数以加快其收敛速度的方法(DE-DQN)。首先,将DQN的网络参数编码为演化个体;其次,分别采用“运行步长”和“平均回报”两种适应度函数评价方式;利用CartPole控制问题进行仿真对比,验证了两种评价方式的有效性。最后,实验结果表明,在智能体训练5 000代时所提出的改进算法,以“运行步长”为适应度函数时,在运行步长、平均回报和累计回报上分别提高了82.7%,18.1%和25.1%,并优于改进DQN算法;以“平均回报”为适应度函数时,在运行步长、平均回报和累计回报上分别提高了74.9%,18.5%和13.3%并优于改进DQN算法。这说明了DE-DQN算法相较于传统的DQN及其改进算法前期能获得更多有用信息,加快收敛速度。

基于多目标函数优化的恒应力加速试验设计

对恒应力加速寿命试验进行了优化设计。首先,选取正常应力下可靠性指标估计的准确程度作为评价加速试验方案优劣的准则,推导出正常应力下对数寿命的极大似然估计(MLE)渐近方差的估计值作为单一优化目标函数;然后,在单一优化目标函数的基础上,考虑到试验代价的因素,推导出恒应力加速寿命试验优化设计的多目标函数;最后,将智能优化算法应用到单一目标优化函数和多目标优化函数的求解,通过实例验证解决了加速试验多目标函数优化的求解问题。

基于改进模糊层次分析法的病险水库除险加固效果评价

为选择可行的加固方案,最大程度地改善病险水库的工作性能,综合考虑除险加固方案的效果可靠性、经济合理性、技术可行性和施工便利性等指标,构建水库除险加固方案多层次优选模型,采用经加速遗传算法改进的模糊层次分析法确定各优选子系统及各指标权重,提出水库加固效果多层次优选评价方法,并选择典型水库进行了验证。结果表明:对于优选子系统,技术可行性和效果可靠性子系统权重较大,分别为0.309和0.298;对于优选指标,综合权重较大的是施工单位水平的高低、稳定性要求满足程度、加固方案与引起大坝加固原因的适应性、加固方案与大坝所处地域适应性等指标。典型水库应用实例中塑性混凝土防渗墙方案综合评价值(0.797)相对较优。

全同态加密软硬件加速研究进展

全同态加密(FHE)是一种重计算、轻交互的多方安全计算协议。在基于全同态加密的计算协议中,尽管计算参与方之间无需多轮交互与大量通信,加密状态下的密态数据处理时间通常是明文计算的10~3~10~6倍,极大地阻碍了这类计算协议的实际落地;而密态数据上的主要处理负担是大规模的并行密码运算和运算所必须的密文及密钥数据搬运需求。该文聚焦软、硬件两个层面上的全同态加密加速这一研究热点,通过系统性地归类及整理当前领域中的文献,讨论全同态加密计算加速的研究现状与展望。