發(fā)布時(shí)間：2019-04-28 08:42

【摘要】：為了準(zhǔn)確高效預(yù)測船舶在海上的航行狀態(tài),以保證人員、貨物和船舶的安全,提出一種自適應(yīng)變異的粒子群優(yōu)化算法(self-adapting particle swarm optimization algorithm,SAPSO),將該算法與誤差反傳(back propagation,BP)神經(jīng)網(wǎng)絡(luò)結(jié)合。SAPSO-BP預(yù)測模型使用SAPSO算法優(yōu)化BP網(wǎng)絡(luò)的網(wǎng)絡(luò)參數(shù)�？朔䝼鹘y(tǒng)BP神經(jīng)網(wǎng)絡(luò)對(duì)初始權(quán)值閾值敏感,容易陷入局部極小值的缺點(diǎn),同時(shí)也克服了傳統(tǒng)PSO算法早熟收斂、搜索準(zhǔn)確度低及迭代效率低等缺點(diǎn)。運(yùn)用該模型對(duì)科研教學(xué)船"育鯤"輪在海上航行的橫搖情況進(jìn)行實(shí)時(shí)預(yù)測實(shí)驗(yàn),驗(yàn)證該方法的可行性與有效性具有較高的預(yù)測精度。
[Abstract]:In order to accurately and efficiently predict the navigation state of ships at sea to ensure the safety of personnel, cargo and ships, an adaptive mutation particle swarm optimization (self-adapting particle swarm optimization algorithm,SAPSO) algorithm is proposed, which is used to reverse transmit errors to (back propagation,. The SAPSO-BP prediction model uses SAPSO algorithm to optimize the network parameters of BP network. The traditional BP neural network is sensitive to the initial weight threshold and easy to fall into the local minimum. At the same time, it also overcomes the shortcomings of the traditional PSO algorithm, such as premature convergence, low search accuracy and low iterative efficiency. The model is used to predict the roll of the ship "Yukun" in the sea, and the feasibility and effectiveness of the method is proved to have high prediction accuracy.
【作者單位】： 大連海事大學(xué)航海學(xué)院;
【基金】：國家自然科學(xué)基金資助項(xiàng)目(51279106,51009017,51379002) 中央高�；究蒲袠I(yè)務(wù)經(jīng)費(fèi)資助項(xiàng)目(3132016116,3132016314) 交通部應(yīng)用基礎(chǔ)研究項(xiàng)目(2014329225010) 遼寧省自然科學(xué)基金資助項(xiàng)目(2014025008)
【分類號(hào)】：U661.321
，

本文編號(hào)：2467498