Using Hopfield neural network to optimize fuel rod loading patterns in VVER/1000 reactor by applying axial variation of enrichment distribution

The present work investigates an appropriate way to solve the problem of optimizing fuel management in a VVER/1000 reactor. To automate this procedure, a computer program has been developed. This program suggests an optimal core configuration which is determined according to established safety constraints. The suggested solution is based on the use of coupled programs, one of which is the nuclear code, for making a database and modeling the core, and another one is the Hopfield neural network. In addition to we applied axial variations of enrichment in fuel rods to flat the flux core as novel role. This computational procedure consists of three main steps. The first one consists of creating the cross section database and calculating neutronic parameters by using WIMSD4 and CITATION codes. The second one consists of finding the best axial variations distributions of enrichment to create a fuel rod pattern by using Hopfield neural network artificial (HNNA) and the cross section database. The third one consists of loading of the fuel rods by the suggested fuel rod patterns and finding the optimum core configuration by HNNA that based on minimizing power peaking factor (PPF, PPF = maximum power/average power) and maximizing the effective multiplication factor (k_eff, the ratio of the number of neutrons in two successive fission generations). The procedure uses the optimized parameters in order to find configurations in which k_eff is maximized. The penalty function is applied to limit the value of local PPF in the neighborhood fuel assemblies. Therefore, in this paper, we proposed a new approach for the use of Hopfield neural network to guide the heuristic search, and applied axial variations distributions of enrichment as novel method to flat the neutron flux and for evaluating the obtained results pertaining to the first core.The results show that applying the HNNA led us to the appropriate PPF and k_eff. Also, applying HNNA and axial variation of enrichment is promising to reach the flattening neutronic flux and guaranteeing safety condition in the reactor core. Therefore, we achieved to a set of two basic parameters PPF and k_eff as effective factors on satisfying the safety constraints of VVER/1000 reactor core.     

基于指数衰减惯性权重的分裂粒子群优化算法

针对粒子群优化算法因种群多样性丧失而陷入局部最优、早熟收敛的问题,提出一种基于指数衰减惯性权重的分裂粒子群优化算法（EDW-DPSO）。首先,采用半均匀初始化种群,使种群以整体均匀、局部随机的方式分布;其次,引入动态分裂算子,对满足分裂条件的粒子执行分裂操作,增加种群多样性,避免粒子陷入局部最优;最后,采用指数衰减的惯性权重,平衡粒子全局搜索和局部开发能力。实验结果表明,该算法在前期有较大的搜索空间,种群多样性增加,后期则强调局部开发,提高收敛精度和优化能力,加快粒子跳脱局部极值逼近全局最优。     

协同智能的蝙蝠差分混合算法

为解决差分进化算法后期收敛易陷入局部最优和早熟收敛的问题,提出一种群体智能优化算法,即协同智能的蝙蝠差分混合算法。利用蝙蝠个体脉冲回声定位的特点,与差分种群相互协作,在当前最优解gbest附近进行一次详细搜索,有效增加种群的多样性,跳出局部最优。通过蝙蝠种群和差分种群两个种群的相互协作,较好平衡全局搜索和局部开发之间的能力。为验证算法有效性,选用9个常用的基准测试函数和5个0-1背包问题,与标准粒子群算法、带高斯扰动的粒子群算法、蝙蝠算法、差分算法、烟花算法相对比,仿真实验表明,所提算法总体性能优于其它5种算法。     

动态调整概率的双重布谷鸟搜索算法

布谷鸟搜索算法是一种新兴的仿生智能算法,存在着求解精度低、易陷入局部最优及收敛速度慢等缺陷,提出了动态调整概率的双重布谷鸟搜索算法(DECS)。首先,在自适应发现概率P中引入了种群分布熵,通过算法的所处迭代阶数和种群分布情况,动态改变发现概率P的大小,有利于平衡布谷鸟算法局部寻优和全局寻优的能力,加快收敛速度;其次,在布谷鸟寻窝的路径位置更新公式中,采用了一种新型步长因子更新寻优方式,形成Levy飞行双重搜索模式,充分搜索空间;最后,在随机偏好游走的更新公式引入非线性对数递减的惯性权重策略,使得算法有效克服易陷入局部最优的缺陷,提高寻优搜索能力。与4种算法相比和19个测试函数的仿真结果表明:改进布谷鸟算法的寻优性能明显提高,收敛速度更快,求解精度更高,具有更强的全局搜索能力和跳出局部最优能力。     

基于改进的Tent混沌万有引力搜索算法

万有引力搜索算法(gravitational search algorithm,GSA)相比于传统的优化算法具有收敛速度快、开拓性能强等特点,但GSA易陷入早熟收敛和局部最优,搜索能力较弱.为此,提出一种基于改进的Tent混沌万有引力搜索算法(gravitational search algorithm based on improved tent chaos,ITC-GSA).首先,改进Tent混沌映射来初始化种群,利用Tent混沌序列随机性、遍历性和规律性的特性使得初始种群随机性和遍历性在可行域内,具有加强算法的全局搜索能力;其次,引入引力常数G的动态调整策略提高算法的收敛速度和收敛精度;再次,设计成熟度指标判断种群成熟度,并使用Tent混沌搜索有效抑制算法早熟收敛,帮助种群跳出局部最优;最后,对10个基准函数进行仿真实验,结果表明所提算法能够有效克服GSA易陷入早熟收敛和局部最优的缺点,提高算法的收敛速度和寻优精度.     

融合多策略的改进麻雀搜索算法

针对麻雀搜索算法收敛速度缓慢、寻优精度不足和容易陷入局部最优等缺点,提出了一种融合正弦搜索策略和多样性变异处理策略的改进麻雀搜索算法。通过引入正弦搜索策略,自适应调整个体权重提高算法收敛速度;针对个体聚集程度过高问题,采用多样性变异处理,引入生物学中种群聚集度的概念和柯西变异对最优解进行扰动,提高算法逃离局部最优的可能。通过九个不同特征的基准函数进行寻优测试,测试结果表明改进算法能够更快地收敛于最优值,有更好的平均值和标准差,表明了其具备更优的收敛速度、收敛稳定性和逃离局部最优值的能力。通过应用该改进优化算法于分数阶PID控制器的参数整定上,进一步验证了改进策略的有效性和可行性。     

基于混合策略改进的鲸鱼优化算法

针对标准WOA算法初始种群分布不均、收敛速度较慢、全局搜索能力弱且易陷入局部最优等问题,提出一种混合策略改进的鲸鱼优化算法。采用Sobol序列初始化种群以使初始解在解空间分布更均匀;通过非线性时变因子和惯性权重平衡并提高全局搜索及局部开发能力,并结合随机性学习策略增加迭代过程中种群的多样性;引入柯西变异提升算法跳出局部最优的能力。通过对12个基准函数和一个水资源需求预测模型的参数估计进行优化实验,结果表明,基于混合策略改进的鲸鱼优化算法在寻优精度及收敛速度上均有明显提升。     

A hybrid AI-based particle bee algorithm for facility layout optimization

Facility layout (FL) design presents a particularly interesting area of study because of its relatively high level of attention to aesthetics and usability qualities, in addition to common engineering objectives such as cost and performance. However, this generally presents a difficult combinatorial optimization problem for engineers. Swarm intelligence, an approach to decision making that integrates collective social behavior models such as the bee algorithm (BA) and particle swarm optimization (PSO), is being increasingly used to resolve various complex optimization problems. In order to integrate BA global search ability with the local search advantages of PSO, this study proposes a new optimization hybrid swarm algorithm—the particle bee algorithm (PBA) which imitates the intelligent swarming behavior of honeybees and birds. This study also proposes a neighborhood-windows technique for improving searching efficiency as well as a self-parameter-updating technique for preventing trapping into a local optimum in high-dimensional problems. This study compares PBA performance against BA and PSO performance in practical FL problem. Results show PBA performance is comparable to those of BA and PSO and can be efficiently employed to solve practical FL problem with high dimensionality.     

融合Sin混沌和分段权值的阿基米德优化算法

针对阿基米德优化算法（Archimedes optimization algorithm,AOA）存在全局搜索能力弱、收敛精度低,易陷入局部最优等问题,提出融合Sin混沌和分段权值的阿基米德优化算法（SAOA）。采用无限折叠迭代的Sin混沌反向学习策略初始化种群,提高初始阶段解的质量,为全局搜索多样性奠定基础;引入算数交叉算子,将当前个体向与全局最优个体进行交叉,引导种群向最优解区域寻优,提高全局搜索能力;引入分段权值策略,平衡算法的全局勘探与局部开发能力,降低算法陷入局部最优的概率;通过对8个测试函数和部分CEC2014函数进行仿真实验及Wilcoxon秩和检验来评估改进算法的寻优性能,实验结果表明改进算法在搜索精度、收敛速度和稳定性等方面均有较大提升。另外,引入优化机械设计案例进行测试分析,进一步验证SAOA在工程优化问题上的可行性和适用性。     

基于切线飞行的麻雀搜索算法

为解决在临近全局最优条件下,原始麻雀搜索算法(sparrow search algorithm, SSA)存在种群多样性降低,局部开发能力薄弱导致不容易跳出局部最优点的问题,提出基于切线飞行的麻雀搜索算法(tangent flight sparrow search algorithm, tanSSA)。首先,使用自适应t分布策略改进发现者位置更新公式,可以提高麻雀个体的寻优能力,同时防止算法早熟。然后,利用切线搜索算法中切线飞行策略所具有的可以增强算法探索搜索空间能力,且能使算法跳出局部最优解的优势,在原始麻雀搜索算法中使用切线飞行扰动策略对最优解进行扰动。这两种策略相结合,可以有效提升tanSSA算法的勘探与开发性能。最后,使用12个标准基准测试函数,结合Wilcoxon秩和检验来测试验证tanSSA算法的优化性能,并与原始SSA算法、鲸鱼优化算法、粒子群优化算法以及自适应t分布SSA算法进行比较。实验证明,基于切线飞行的麻雀搜索算法的寻优能力和收敛速度都有显著提升。