Research Status and Prospect of Target Tracking Technologies via Underwater Sensor Networks
-
摘要: 水下目标跟踪在海洋资源的开发利用以及国家安全的防御等方面都具有广泛的应用价值和重要的战略意义. 基于水下传感器网络(Underwater sensor networks, USNs)的目标跟踪技术凭借其覆盖范围广、观测时间长和实时融合等优势已经成为一个新的研究热点. 本文针对基于USNs的目标跟踪关键技术的基本思想、研究进展、应用及局限性进行了综述, 主要从以下几个角度对其展开论述: USNs的建设现状、系统组成及其分类、目标跟踪系统模型、单目标跟踪技术、多目标跟踪技术以及能效优化措施. 最后, 本文不仅指出了基于USNs的目标跟踪研究目前存在的主要挑战, 并对该领域的未来发展方向进行了展望.Abstract: Underwater target tracking has extensive application value and important strategic significance in the development and utilization of marine resources, and national security defense. Target tracking technology via underwater sensor networks (USNs) has become a new research hotspot for its wide coverage, long observation time and real-time fusion. This paper gives a review of the basic ideas, research progresses, applications, and limitations of those key technologies of target tracking via USNs. It is mainly discussed from the following respects: the construction status of USNs, system composition and classification, target tracking system model, single target tracking technoligies, multi-target tracking technoligies, and energy efficiency optimization measures. Furthermore, this paper not only points out the main challenges of researches of target tracking via USNs, but also prospects the future development direction of the field.
-
电熔镁砂是一种生产航天、航空和工业所需耐火材料的原料. 电熔镁砂生产过程采用多台电熔镁炉, 熔炼菱镁矿石, 生产电熔镁砂. 电熔镁炉是一种重大耗能设备, 耗电成本占总生产成本的60%以上[1-2]. 需量是电熔镁砂生产过程的耗电指标, 供电部门规定需量为当前时刻和过去29个采样时刻的电熔镁砂生产用电功率的均值, 其采样周期为7秒[3]. 电熔镁砂生产企业采用需量监控系统监控需量值, 当需量达到其限幅值(22 300 kW)时会切断其中一台电熔镁炉的供电, 使需量不超过限幅值, 然而切断供电会破坏炉内温度场吸热和放热平衡, 降低产品质量[4].
在电熔镁砂生产过程中, 当原料杂质成分含量增大和颗粒大小变化等造成阻抗减小, 导致熔化电流增大、功率增大, 进而需量上升. 由于熔化电流设定值不变, 因此熔化电流控制系统使熔化电流下降, 需量下降, 出现需量先升后降的尖峰现象. 当需量尖峰值达到其限幅值会造成拉闸断电, 为了避免需量尖峰造成的不必要的断电, 需要对需量尖峰进行识别, 因此需要对需量进行多步预报.
需量多步预报的研究集中在城市用电领域. 文献[5]利用采样周期为1小时的用电需量数据, 提出一种自回归模型与三次样条曲线相结合的混合负荷多步预报方法, 预报大西洋城未来一天每小时的用电需量. 文献[6]利用采样周期为0.5小时的用电需量数据, 提出基于信号滤波和季节调整的多输出前馈神经网络与经验模态分解相结合的多步预报模型, 预报澳大利亚新南威尔士州未来一天每半小时的用电需量. 文献[7]利用采样周期为1分钟的需量数据, 提出基于非线性自回归神经网络的多步预报方法, 预报未来1分钟、10分钟、1小时和2小时的住宅用电需量. 文献[8]利用采样周期为0.5小时的用电需量数据, 提出基于多目标优化算法的最小二乘支持向量机的多步预报方法, 预报电力市场未来0.5小时、1小时、2小时和3小时的用电需量. 文献[9]利用采样周期为1天的用电需量数据, 提出基于支持向量机的多步预报模型, 预报某配电公司未来30天的每天最大用电需量. 文献[10]利用采样周期为0.5小时的用电需量数据, 提出基于支持向量机、极限学习机和多层循环神经网络的用电需量多步预报方法, 预报了未来1.5小时的每半小时的城市用电需量. 文献[11]利用采样周期为1小时的用电需量数据, 提出基于自回归滑动平均模型的某地区未来一天的用电需量预报方法. 文献[12]利用采样周期为1个月的用电需量数据, 提出基于多层神经网络的未来12个月的地区用电需量预报模型. 文献[13]利用采样周期为1个月的用电需量数据, 提出基于神经网络的未来12个月的地区用电需量预报方法. 文献[14]利用采样周期为15分钟的用电需量数据, 提出基于变分模态分解的某地区未来1分钟、3分钟和5分钟的用电需量预报方法. 文献[15]利用采样周期为30秒的用电需量数据, 提出基于集成经验模态分解和卷积神经网络的某地区未来30秒、1分钟、1.5分钟和2分钟的用电需量预报方法. 电熔镁砂生产用电需量的变化是快变化的动态系统, 需量的采样周期为7秒, 发生需量尖峰的整个时间在70秒之内. 由于电熔镁砂生产过程是由多台电熔镁炉运行组成, 其用电需量变化过程是模型结构与系统阶次未知的非线性动态系统, 而城市用电需量变化是一个慢变化的系统, 可以采用上述静态建模方法[5-15]. 电熔镁砂生产用电需量的多步预报难以采用文献[5-15]方法进行需量尖峰的准确预报.
文献[16-17]利用采样周期为7秒的用电需量数据, 提出数据与模型驱动的电熔镁砂生产用电需量单步预报方法. 为了提高需量预报精度, 文献[18]采用用电需量大数据提出系统辨识与自适应深度学习相结合的电熔镁砂生产用电需量一步预报方法. 由于需量尖峰是需量先升高后下降, 需要对需量进行多步预报.
本文利用电熔镁砂生产过程熔化电流闭环控制系统方程, 建立了由线性模型和未知非线性动态系统组成的群炉需量多步预报模型, 将系统辨识与自适应深度学习相结合, 采用端边云协同结构, 提出了电熔镁砂生产用电需量多步智能预报方法. 采用电熔镁砂生产过程的工业大数据验证了所提方法可以准确预报用电需量的变化趋势.
1. 电熔镁砂需量监控过程描述
如图1所示, 电熔镁砂的生产过程由多台电熔镁炉控制系统, 供电系统和需量监控系统组成, 每台电熔镁炉控制系统由电熔镁炉、拉闸系统、加料系统、熔化电流控制系统组成[2]. 需量监控系统由功率采集装置和需量监控计算机组成. 电熔镁炉采用埋弧方式, 通过加料系统将原矿送入电熔镁炉内, 电流控制系统控制三相电极与原料之间的距离使产生的电弧电流达到生产工艺规定的熔化电流, 形成熔池. 边熔化边加料, 使熔池增高至炉口, 熔炼过程结束. 熔炼过程持续约10小时, 每台电熔镁炉每炉次耗电约40 MWh, 因此电熔镁炉是高耗能设备.
图 1 电熔镁砂生产用电需量监控流程图Fig. 1 An flow chart of electricity demand monitoring process for a fused magnesia production为了节能减排, 电力部门规定当前时刻和过去29个时刻的功率的平均值作为当前时刻的需量值并规定了需量的限幅值, 当需量实际值超过需量限幅值对用电企业罚款, 因此生产企业设立需量监控系统, 操作人员监视需量实际值, 当超过限幅值, 通过拉闸系统切断其中一台电熔镁炉的电源. 由于电熔镁砂生产过程常出现尖峰现象, 导致不必要的拉闸. 为避免尖峰导致的不必要的拉闸断电, 需要对尖峰进行预报, 由于尖峰现象是需量先升高后下降, 因此需要对需量进行多步预报.
2. 电熔镁砂生产用电需量多步预报模型
需量$ \bar{p}(k) $为$ k $时刻群炉功率$ p(k) $与过去29个采样周期的群炉功率的均值, 即
$$ \begin{split} \bar{p}(k)=\;& \frac{1}{30}\sum_{j = 0}^{29} p(k-j) =\\ &\bar{p}(k-1)+\frac{p(k)-p(k-30)}{30} \end{split} $$ (1) 其中, $ k = 1 $表示采样周期7秒, $ (k+n) $时刻的需量$\bar{p}(k+n)$为
$$ \begin{split} \bar{p}(k+n) = &\frac{1}{30}\sum_{j = 0}^{29} p(k+n-j)=\frac{1}{30}\sum_{i = 0}^n{p}(k+n-i)\;+\\&\frac{1}{30}\sum_{j = 0}^{29-n} p(k-j)=\bar{p}(k)\;-\\ &\frac{1}{30}\sum_{i = 0}^n{p}(k-30+i)+\frac{1}{30}\sum_{i = 1}^n p(k+i)\ \end{split} $$ (2) 其中, 群炉功率$ p(k+1), \cdots, p(k+n) $未知, 因此需要建立群炉功率多步预报模型.
2.1 群炉功率多步预报模型
首先需建立群炉功率$ p(k) $的动态模型. 电熔镁炉群炉功率$ p(k) $为 $M$个电熔镁炉功率之和$ \sum_{s = 1}^M p_s(k) $.
采用文献[18]的方法建立第$ s $个电熔镁炉的功率$ p_s(k) $的动态模型. 第$ s $个电熔镁炉的熔化电流$ y_s(k) $为电流闭环控制系统的输出, 其动态模型为
$$ \begin{align} T_s(z^{-1})y_s(k) = G_s(z^{-1})y^*+v_s(k) \end{align} $$ (3) 其中, $ y^* $是已知的熔化电流设定值, $ v_s(k) $为未知非线性项, $ T_s(z^{-1}) $ 和 $ G_s(z^{-1}) $为关于$ z^{-1} $的多项式, 即$ T_s(z^{-1}) = 1+t_{s1}(z^{-1})+t_{s2}(z^{-2})+t_{s3}(z^{-3}) $, $G_s(z^{-1}) = g_{s0}+g_{s1}(z^{-1})+g_{s2}(z^{-2})$.
第$ s $个电熔镁炉的功率动态模型为
$$ \begin{split} p_s(k) =\; &\sqrt{3}Uy_s(k)\cos \phi =-\;t_{s1}p_s(k-1)\;-\\ &t_{s2}p_s(k-2)-t_{s3}p_s(k-3)\;+\\ &d_{s0}p^*+v_s(k) \end{split} $$ (4) 其中, $ p^* $是熔化电流设定值 $ y^* $对应的功率; $p_s(k- 1) $, $p_s(k-2) $, $ p_s(k-3)$为$ (k-1) $, $ (k-2) $, $(k- 3) $时刻的第$s$个电熔镁炉功率; $d_{s0} =g_{s0}+ g_{s1}+ g_{s2} $.
采用未知常数$ t_{1}, t_{2}, t_{3}, d_{0} $代替式(4)中的$ t_{s1}, t_{s2}, t_{s3}, d_{s0} $, 群炉功率$ p(k) $为
$$ \begin{split} p(k) =\; &\sum_{s = 1}^{M} p_s(k)= -\;t_{1}p(k-1)-t_{2}p(k-2)\;-\\ &t_{3}p(k-3)+d_{0}p^*+v(k) \end{split} $$ (5) 其中, $ v(k) $为$v(k) = \sum_{s = 1}^{M}\left((t_1-t_{s1})p(k-1)+\right. (t_2-$ $t_{s2})p(k-2) $ $+\;(t_3\;-\;t_{s3})p(k-3)\;-\;(d_0\;-\;d_{s0})p^*\;+$ $v_s(k) ). $
由式(5)可得$ (k+1) $时刻的群炉功率$ p(k+1) $为
$$ \begin{split} {p}(k+1) =\; &{\boldsymbol{\varphi}}(k){{\boldsymbol{\theta}}}^1+{v}(k+1)=\\ &{\boldsymbol{\varphi}}(k){{\boldsymbol{\theta}}}^1+{r}(k+1) \end{split} $$ (6) 其中, ${\boldsymbol{\varphi}}(k) \,= \,( p(k),\, p(k-1),\, p(k-2), p(k-3) )$, $ {{\boldsymbol{\theta}}}^1 = ( {\theta}_1^1, {\theta}_2^1, {\theta}_3^1, {\theta}_4^1)^{\rm{T}} = (-t_{1}, -t_{2}, -t_{3}, d_{0})^{\rm{T}} $, ${r}(k\;+ 1) = {v}(k+1).$ $ (k+2) $时刻的群炉功率 $ p(k+2) $为
$$ \begin{split} {p}(k+2) =\; &{\boldsymbol{\varphi}}(k+1){\boldsymbol{\theta}}^1+v(k+2)=\\ &({\boldsymbol{\varphi}}(k){{\boldsymbol{\theta}}}^1+{v}(k+1), p(k), p(k-1),\\ & p^* ){\boldsymbol{\theta}}^1+v(k+2)=\\ &p(k)((\theta_1^1)^2+\theta_2^1)+p(k-1)(\theta_1^1\theta_2^1+\theta_3^1)\;+\\ &p(k-2)\theta_3^1\theta_1^1+p^*(\theta_1^1\theta_4^1+\theta_4^1)\;+\\ &r(k+1)\theta_1^1+v(k+2)=\\ &{\boldsymbol{\varphi}}(k){{\boldsymbol{\theta}}}^2(k)+r(k+2) \\[-10pt]\end{split} $$ (7) 其中, 线性模型参数${{\boldsymbol{\theta}}}^2 = ({\theta}_1^2, {\theta}^2_{2}, {\theta}^2_{3}, {\theta}^2_{4})^{\rm{T}},{\theta}_1^2 = (\theta_1^1)^2\, +$ $\theta_2^1, {\theta}^2_{2} = \theta_1^1\theta_2^1+\theta_3^1, {\theta}^2_{3} = \theta_3^1\theta_1^1, {\theta}^2_{4} = \theta_1^1\theta_4^1+\theta_4^1$, 未知非线性项$ r(k+2) $ 为 ${r}(k+2) \;=\; {r}(k+1)\theta_1^1(k+1)\;+ v(k+2)$.
采用数学归纳法可以证明假设$ (k+n-1) $时刻的群炉功率$ p(k+n-1) $为式(8)成立, 则$ (k+n) $时刻的群炉功率$ p(k+n) $表达式(9)成立
$$ {p}(k+n-1) = {\boldsymbol{\varphi}}(k){{\boldsymbol{\theta}}}^{n-1}+ {r}(k+n-1) $$ (8) $$ {p}(k+n) = {\boldsymbol{\varphi}}(k){{\boldsymbol{\theta}}}^n+ {r}(k+n) $$ (9) 其中, ${{\boldsymbol{\theta}}}^{n-1} = ({\theta}_1^{n-1}, {\theta}^{n-1}_{2}, {\theta}^{n-1}_{3}, {\theta}^{n-1}_{4})^{\rm{T}}$, ${{\boldsymbol{\theta}}}^n = ({\theta}_1^n,$${\theta}_2^n, {\theta}^n_{3}, {\theta}^n_{4})^{\rm{T}}, {\theta}_1^n = {\theta}_1^{n-1}\theta_1^1+{\theta}_1^{n-2}\theta_2^1+{\theta}_1^{n-3}\theta_3^1$, ${\theta}_2^n = $ ${\theta}_2^{n-1}\theta_1^1+{\theta}_2^{n-2}\theta_2^1+{\theta}_2^{n-3}\theta_3^1$, $ {\theta}_3^n = {\theta}_3^{n-1}\theta_1^1+{\theta}_3^{n-2}\theta_2^1\;+ $ ${\theta}_3^{n-3}\theta_3^1 $, $ {\theta}_4^n = {\theta}_4^{n-1}\theta_1^1+{\theta}_4^{n-2}\theta_4^1+{\theta}_4^{n-3}\theta_3^1+\theta_4^1$, 未知非线性项$ {r}(k+n) $为${r}(k+n) = {r}(k+n- 1)\theta_1^1+{r}(k\;+ n-2)\theta_2^1+{r}(k+n-3)\theta_3^1+{v}(k+n)$. 因此群炉功率多步预报模型为
$$ \begin{align} {P}(k+n) = &\Theta^{\rm{T}}\varphi^{\rm{T}}(k)+ {R}(k+n) \end{align} $$ (10) 其中, $ {P}(k+n) = (p(k+1), \cdots, p(k+n))^{\rm{T}} $, 模型参数$ \Theta = ({\boldsymbol{\theta}}^1, \cdots, {\boldsymbol{\theta}}^n) $, $R(k+n) = (r_1(k+1), \cdots, r_i(k\,+ i), \cdots, r_n(k+n))^{\rm{T}}$.
由式(10)可知模型参数$ \Theta $的辨识方程为
$$ \begin{align} P_s(k) = \begin{pmatrix} {\boldsymbol{\varphi}}(k-1){\boldsymbol{\theta}}^1\\ \vdots\\ {\boldsymbol{\varphi}}(k-i){\boldsymbol{\theta}}^i\\ \vdots\\ {\boldsymbol{\varphi}}(k-n){\boldsymbol{\theta}}^n \end{pmatrix} + {R_s}(k) \end{align} $$ (11) 其中, $ n\times 1 $的向量$ P_s(k+n) $为
$$ P_s(k+n) = (p(k), \cdots, p(k))^{\rm{T}} $$ $$ {R_s}(k) = (r_1(k), \cdots, r_i(k), \cdots, r_n(k))^{\rm{T}} $$ 采用最小二乘算法[19]离线辨识模型参数$ \Theta $, 由式(10)和式(11)可得群炉功率预报模型为
$$ \begin{align} {P}(k+n) = \hat{\Theta}^{\rm{T}}{\boldsymbol{\varphi}}^{\rm{T}}(k)+ \bar{R}(k+n) \end{align} $$ (12) 其中, $\hat{\Theta}^{\rm{T}} = ({\hat{\boldsymbol{\theta}}}^1, \cdots, {\hat{\boldsymbol{\theta}}}^n), \bar{R}(k+n) = (\Theta-\hat{\Theta}^{\rm{T}})\varphi^{\rm{T}}(k)\,+$ $R(k+n) = (\bar{r}_1(k+1), \cdots, \bar{r}_i(k+i), \cdots, \bar{r}_n(k + n))^{\rm{T}}$,
$$ \begin{split} \bar{r}_i(k+i) =\;& f_i(p(k), p(k-1), \cdots, \\ &\bar{r}_i(k), \bar{r}_i(k-1), \cdots) \end{split} $$ (13) 其中, $ f(\cdot) $是模型结构与阶次未知的未知非线性函数, $i = 1, \cdots, n$. 由式(11)知
$$ \begin{align} {\bar{R}_s}(k) = P_s(k)- \begin{pmatrix} {\boldsymbol{\varphi}}(k-1){\hat{\boldsymbol{\theta}}}^1\\ \vdots\\ {\boldsymbol{\varphi}}(k-i){\hat{\boldsymbol{\theta}}}^i\\ \vdots\\ {\boldsymbol{\varphi}}(k-n){\hat{\boldsymbol{\theta}}}^n \end{pmatrix} \end{align} $$ (14) 其中, $ \bar{R}_s(k) = \left(\bar{r}_{1}(k), \cdots, \bar{r}_{i}(k), \cdots, \bar{r}_{n}(k)\right) $.
2.2 需量多步预报模型
由式(2)和式(12)可以得到需量多步预报模型为
$$ \begin{split} \bar{P}\left( k+n \right) =\; &\left( \begin{matrix} \bar{p}(k) \\ \bar{p}(k) \\ \vdots \\ \bar{p}(k) \\ \end{matrix} \right)-\frac{1}{30}\left( \begin{matrix} p(k-29) \\ \displaystyle\sum\limits_{i = 1}^{2}{p(k-30+i)} \\ \vdots \\ \displaystyle\sum\limits_{i = 1}^{n}{p(k-30+i)} \\ \end{matrix} \right)+\\ & \frac{1}{30}\left( \begin{matrix} p(k\text+1) \\ \displaystyle\sum\limits_{i = 1}^{2}{p(k+i)} \\ \vdots \\ \displaystyle\sum\limits_{i = 1}^{n}{p(k+i)} \end{matrix} \right) =\\ &\left( \begin{matrix} \bar{p}(k) \\ \bar{p}(k) \\ \vdots \\ \bar{p}(k) \end{matrix} \right)-\frac{1}{30}\left( \begin{matrix} p(k-29) \\ \displaystyle\sum\limits_{i = 1}^{2}{p(k-30+i)} \\ \vdots \\ \displaystyle\sum\limits_{i = 1}^{n}{p(k-30+i)} \end{matrix} \right)+\\ &\frac{1}{30}\left( \begin{matrix} {\boldsymbol{\varphi}} (k){{{\hat{\theta }}}^{1}} \\ \displaystyle\sum\limits_{i = 1}^{2}{{\boldsymbol{\varphi}} (k){{{\hat{\theta }}}^{i}}} \\ \vdots \\ \displaystyle\sum\limits_{i = 1}^{n}{{\boldsymbol{\varphi}} (k){{{\hat{\theta }}}^{i}}} \\ \end{matrix} \right)+\frac{1}{30}\left( \begin{matrix} \bar{r}(k) \\ \displaystyle\sum\limits_{i = 1}^{2}{\bar{r}(k+i)} \\ \vdots \\ \displaystyle\sum\limits_{i = 1}^{n}{\bar{r}(k+i)} \\ \end{matrix} \right) =\\ &{\bar{P}_S(k)}+\frac{1}{30}AP(k+n-30)\;+\\ &\frac{1}{30}A\hat{\Theta}^{\rm{T}}{\boldsymbol{\varphi}}^{\rm{T}}(k)+ \frac{1}{30}A\bar{R}(k+n) \\[-10pt]\end{split} $$ (5) 其中, $\bar{P}(k+n) = (\bar{p}(k+1), \cdots, \bar{p}(k+n))^{\rm{T}}$, ${\bar{P}_S(k)} = (\bar{p}(k), \cdots, \bar{p}(k))^{\rm{T}}$, $P(k+n-30) = (p(k-29), \cdots, p(k-n+30))^{\rm{T}}$, $ \bar{R}(k+n) $ 为 $(\bar{r}_1(k), \cdots, \bar{r}_i(k+ i), \cdots, \bar{r}_n(k+n))^{\rm{T}}$, $ A $为非0元素为1的$ n\times n $维下三角阵. 式(15)中$ {\bar{P}_S(k)}, P(k+n-30), \hat{\Theta}^{\rm{T}}{\boldsymbol{\varphi}}^{\rm{T}}(k) $已知, 向量$ \bar{R}(k+n) $是模型结构阶次与参数未知的非线性动态系统.
3. 需量多步智能预报方法
3.1 需量多步预报策略
采用文献[18]方法建立式(15)的未知非线性动态系统的由在线深度学习多步预报模型、自校正深度学习多步预报模型和自校正机制组成的自适应深度学习多步预报模型.
采用图2所示的端边云协同结构实现电熔镁砂生产用电需量多步智能预报算法, 其中端−需量监控系统实时采集电熔镁砂生产过程中的群炉功率$ p(k) $与需量$ \bar{p}(k) $, 边−需量预报计算机执行数据处理、在线计算$ \hat{\Theta}^{\rm{T}}\varphi^{\rm{T}}(k) $, 采用窗口长度为$ N $的数据和$ \bar{R}(k\;+ n) $的在线深度学习多步预报模型获得$ \hat{\bar{R}}(k+n) $, 采用式(15)求取需量多步预报值$ \hat{\bar{P}}(k+n) $, 云−数据服务器和人工智能计算平台采用$ k $时刻以及以前所有时刻的输入输出数据和$ \bar{R}(k+n) $的自校正深度学习多步预报模型更新自校正深度学习多步预报模型的全部权值参数和偏置参数. 自校正机制在线监控$ \bar{R}(k+n) $的在线深度学习多步预报模型的预报精度, 当不满足精度要求时, 采用自校正深度学习多步预报模型的参数校正在线深度学习多步预报模型的参数, 从而保证需量的预报精度.
图 2 端边云协同需量多步智能预报结构图Fig. 2 Schematic of multi-step intelligent forecasting of demand with edge-cloud coordination3.2 $ \bar{R}(k+n) $的自适应深度学习多步预报算法
首先建立$ \bar{R}(k+n) $的自适应深度学习多步预报算法. 采用长短周期记忆(Long short-term memory, LSTM)[20-22]的网络架构提出如图3所示的需量第$ i $步预报$ \bar{r}(k+i) $的深度学习预报模型结构. 结合$ \bar{r}(k+i) $动态特性, 将其输入变量作为单个神经元的输入, 未知阶次用神经元个数$ t $来表示, 由式(13)和式(14)可知$ \bar{r}(k+i) $的深度学习网络的第$ j $个神经元的输入为 ${\boldsymbol{x}}_i(k-j+1) = (p(k- j\;+ 1), \bar{r}_i(k-j+1))^{\rm{T}}$, 其中 $\bar{r}_i(k-j+1) = p(k- j\;+ 1)-{\boldsymbol{\varphi}}(k- i-j+1){\hat{\boldsymbol{\theta}}}^i$, $ j = 1, \cdots, t $. 采用文献[18]的训练方法, 利用30个炉次(150000组)的群炉功率数据离线训练$ \bar{r}(k+i) $的深度学习模型结构, 确定神经元个数$ t = 25 $、神经元的节点个数$ \bar{h} = 200 $、隐藏层数$ L = 3 $、在线训练数据窗口长度$ N = 2\,000 $. 采用该深度学习预报模型结构, 提出由在线深度学习预报模型、自校正深度学习预报模型和自校正机制组成的$ \bar{r}(k+i) $的自适应深度学习预报算法.
图 3 $ \bar{r}(k+i)$的深度学习预报模型结构Fig. 3 Structure of deep learning prediction model of $ \bar{r}(k+i)$采用窗口长度$ N $的实时数据在线校正$ \bar{r}(k+i) $的在线深度学习预报模型的输出层权值与偏置参数. 校正算法为
$$ \begin{align} \hat{\bar{r}}_i(k+i) = {\hat{\boldsymbol{\beta}}}_i(k){\boldsymbol{h}}_i^3(k)+\hat{b}_i(k) \end{align} $$ (16) 其中,
$$ {\hat{\boldsymbol{\beta}}}_i(k) = {\hat{\boldsymbol{\beta}}}_i(k-1)-\alpha\frac{\partial L_i(k)}{\partial {{\boldsymbol{\beta}}}_i(k-1)} $$ (17) $$ \hat{b}_i(k) = \hat{b}_i(k-1)-\alpha\frac{\partial L_i(k)}{\partial{b}_i(k-1)} $$ (18) $$ L_i(k) =\frac{1}{N}\sum_{m = 0}^{N-1}||\Delta \bar{r}_i(k-m)||_2 $$ (19) 其中, $ \Delta\bar{r}_i(k-m) = \bar{r}_i(k-m)-\hat{\bar{r}}_i(k-m) $.
采用当前时刻$ k $以及以前所有时刻的实时数据校正自校正深度学习预报模型的全部权值和偏置参数. 其输出层的权值与偏置参数采用式(16) ~ (19)校正. 第$ l $层第$ j $个神经元的输出
$$ \begin{split} {\boldsymbol{h}}_i^l(k-j+1) =\;& {\boldsymbol{o}}_i^l(k-j+1) \;\odot\\ &\tanh( C_i^l(k-j+1)) \end{split} $$ (20) 其中, $ \odot $为哈达玛积[22], $ \tanh(\cdot) $为双曲正切函数, $ ( C_i^l(k-j+1)) $和$ {\boldsymbol{o}}_i^l(k-j+1) $表示第$ l $层第$ j $个神经元的状态和输出门的输出, 采用文献[12]方法计算, 其中, 第$ l $层第$i $个神经元的输出门的权值与偏置参数的校正算法为
$$ W_i^l(k-j+1) = W_i^l(k-j)-\alpha\frac{\partial L_i(k)}{\partial W_i^l(k-j)} $$ (21) $$ b_i^l(k-j+1) = b_i^l(k-j)-\alpha\frac{\partial L_i(k)}{\partial b_i^l(k-j)} $$ (22) $$L_i(k) =\frac{1}{k}\sum_{m = 0}^{k-1}||\Delta \bar{r}_i(k-m)||_2 $$ (23) 其中, $ \Delta\bar{r}_i(k-m) = \bar{r}_i(k-m)-\tilde{r}_i(k-m) $.
为了准确预报需量尖峰, 需要保证需量预报误差精度和需量变化趋势预报精度, 由式(15)知需量预报精度取决于$ \bar{r}(k+i) $的预报精度. 采用自校正机制监控$ \bar{r}(k+i) $的在线深度学习预报模型的预报误差和变化趋势的预报精度, 当不满足精度要求时, 采用自校正深度学习预报模型的各层权值参数与偏置参数校正在线深度学习预报模型的权值参数与偏置参数.
自校正机制采用$ \bar{r}(k+i) $的预报误差$ \Delta \bar{r}_i(k) $, 未知非线性系统第$ i $步上升趋势预报准确率$ { TPR_i(k)} $和第$ i $步下降趋势预报准确率$ { TNR_i(k)} $三项指标, 即
$$ |\Delta\bar{r}_i(k)| = |\bar{r}_i(k)-\hat{\bar{r}}_i(k)| $$ (24) $$ { TPR_i(k)} = \frac{\sum\limits_{m = 0}\limits^{N-1}{ TP}_i(k-m)}{\sum\limits_{m = 0}\limits^{N-1}{ TP}_i(k-m)+\sum\limits_{m = 0}\limits^{N-1}{ FP}_i(k-m)} $$ (25) $$ { TNR_i(k)} =\frac{\sum\limits_{m = 0}\limits^{N-1}{ TN}_i(k-m)}{\sum\limits_{m = 0}\limits^{N-1}{ TN}_i(k-m)+\sum\limits_{m = 0}\limits^{N-1}{ FN}_i(k-m)} $$ (26) 其中, $ {TP}_i(k), { FP}_i(k), { TN}_i(k), { FN}_i(k) $的计算方式如表1所示.
表 1 $ { TP}_i(k), { FP}_i(k), { TN}_i(k), {FN}_i(k)$的计算方式Table 1 Formula mode of ${ TP}_i(k), { FP}_i(k), $ ${ TN}_i(k), {FN}_i(k) $$\hat{\bar{r} }_i(k)-\hat{\bar{r} }_i(k-1)\geq 0$ $\hat{\bar{r} }_i(k)-\hat{\bar{r} }_i(k-1) < 0$ $\bar{r}_i(k)-\bar{r}_i(k-1)\geq 0$ ${TP}_i(k)=1$ ${FP}_i(k)=1$ $\bar{r}_i(k)-\bar{r}_i(k-1)< 0$ ${FN}_i(k)=1$ ${TN}_i(k)=1$ $ k $时刻在线深度学习预报模型的预报误差$ |\Delta\bar{r}_i(k)|\geq \delta_i $ ($ \delta_i $为预报误差上界), 自校正深度学习预报模型的预报误差$ |\Delta\bar{r}_i(k)|< \delta_i $, 且在线深度学习预报模型的上升趋势和下降趋势预报准确率均小于自校正深度学习预报模型的上升趋势和下降趋势预报准确率, 采用自校正深度学习预报模型的全部权值参数和偏置参数校正在线深度学习预报模型的全部权值参数和偏置参数.
3.3 需量多步智能预报算法
由式(15)可得需量多步预报模型为
$$ \begin{split} \hat{\bar{P}}(k+n) =\; &{\bar{P}_S(k)}-\frac{1}{30}AP(k+n-30)\;+\\ &\frac{1}{30}A\hat{\Theta}^{\rm{T}}\varphi^{\rm{T}}(k)+ \frac{1}{30}A\hat{\bar{R}}(k+n) \end{split} $$ (27) 其中,
$$ \begin{split} \hat{\bar{P}}(k+n) =\;& (\hat{\bar{p}}_1(k+1), \cdots, \hat{\bar{p}}_i(k+i), \cdots,\\ &\hat{\bar{p}}_n(k+n))^{\rm{T}}\\ \hat{\bar{R}}(k+n) =\;&(\hat{\bar{r}}_1(k+1), \cdots, \hat{\bar{r}}_i(k+i), \cdots,\\ &\hat{\bar{r}}_n(k+n))^{\rm{T}} \end{split} $$ 端边云协同的需量多步智能预报算法:
1)端−需量监控系统实时采集电熔镁砂生产过程中的群炉功率$ p(k) $与需量$ \bar{p}(k) $;
2) 边−需量预报计算机执行数据处理和需量在线多步预报模型. 在线计算$ \hat{\Theta}^{\rm{T}}\varphi^{\rm{T}}(k) $, 由式(14)计算$ \hat{\bar{R}}(k+n) $. 采用窗口长度为$ N $的输入输出数据由$ \bar{R}(k+n) $的在线深度学习多步预报模型得其预报值$ \hat{\bar{R}}(k+n) $, 由需量多步预报模型式(27)得需量多步预报值$ \hat{\bar{P}}(k+n) $;
3)云−数据服务器和人工智能计算平台采用$ k $时刻以及以前所有时刻的输入输出数据和$ \bar{R}(k+n) $的自校正深度学习多步预报模型得其预报值$ \hat{\bar{R}}(k+ n) $. 采用自校正机制的三项指标式(24) ~ (26), 当$ \bar{R}(k+n) $的在线深度学习多步预报模型的预报误差超过预报精度上界时, 采用自校正深度学习多步预报模型的权值参数和偏置参数校正在线深度学习多步预报模型的权值参数和偏置参数.
4. 实验结果
采用某电熔镁砂生产企业的实际功率和需量数据进行了本文提出的需量多步智能预报方法的实验, 并与文献[9]提出的基于支持向量机、极限学习机和循环神经网络的用电需量多步预报方法进行了对比实验.
采用30个炉次的150000组功率数据离线确定$ \bar{r}(k+i) $的深度学习预报模型结构, 神经元个数$ t = 25 $、神经元的节点个数$ \bar{h} = 200 $、隐藏层数$ L = 3 $. 校正算法中的式(17)、式(18)、式(21)和式(22)中的学习率为$ \alpha = 0.1 $, 在线训练数据窗口长度$ N = 2\,000 $. 自校正机制中的预报误差上界$ \delta_i = 100 $.
由于发生需量尖峰的整个时间小于70秒, 而需量的采样周期为7秒, 因此选择需量预报步数$ i = 1, \cdots, 10 $. 采用线性模型参数辨识方程式(11)得模型参数$ \hat{\Theta} $为
$$ \begin{split} &{{{\hat{\boldsymbol{\theta}} }}^{1}} = {{\left( {0}{.140, 0}{.075, -0}{.157, 0}{.869} \right)}^{\rm T}}\\ & {{{\hat{\boldsymbol{\theta}} }}^{2}} = {{\left( {0}{.201, 0}{.135, -0}{.042, 0}{.587} \right)}^{\rm T}} \\ & {{{\hat{\boldsymbol{\theta}} }}^{3}} = {{\left( {0}{.204, 0}{.146, 0}{.061, 0}{.431} \right)}^{\rm T}}\\ &{{{\hat{\boldsymbol{\theta}} }}^{4}} = {{\left( {0}{.201, 0}{.109, 0}{.103, 0}{.411} \right)}^{\rm T}} \\ & {{{\hat{\boldsymbol{\theta}} }}^{5}} = {{\left( {0}{.203, 0}{.103, 0}{.068, 0}{.427} \right)}^{\rm T}}\\ &{{{\hat{\boldsymbol{\theta}} }}^{6}} = {{\left( {0}{.207, 0}{.103, 0}{.063, 0}{.409} \right)}^{\rm T}} \\ & {{{\hat{\boldsymbol{\theta}} }}^{7}} = {{\left( {0}{.208 , 0}{.103 , 0}{.066, 0}{.389} \right)}^{\rm T}} \\ &{{{\hat{\boldsymbol{\theta}} }}^{8}} = {{\left( {0}{.204, 0}{.103, 0}{.069, 0}{.374} \right)}^{\rm T}}\\ &{{{\hat{\boldsymbol{\theta}} }}^{9}} = {{\left( {0}{.203, 0}{.097, 0}{.071, 0}{.364} \right)}^{\rm T}}\\ &{{{\hat{\boldsymbol{\theta}} }}^{10}} = {{\left( {0}{.202, 0}{.095, 0}{.067, 0}{.358} \right)}^{\rm T}}\end{split} $$ 采用上述30个炉次的150000组需量数据离线建立文献[9]的用电需量多步预报模型:
$$ \begin{split} \hat{\bar{p}}(k+i) =\; &{{W}_{1}}{{\hat{\bar{p}}}_{svm}}(k+i)+{{W}_{2}}{{\hat{\bar{p}}}_{elm}}(k+i)\;+\\ &{{W}_{3}}{{\hat{\bar{p}}}_{rnn}}(k+i) \end{split} $$ 其中, $ \hat{\bar{p}}_{svm}, \hat{\bar{p}}_{elm}, \hat{\bar{p}}_{rnn} $分别为支持向量机、极限学习机和循环神经网络的输出, 上述模型的阶次$ t = 25 $, 支持向量机中径向基函数的期望为150、方差为0.08, 循环神经网络的每层节点数为$ \bar{h} = 150 $, 隐藏层数为$ L = 2 $, 权参数$W_1 = 0.16, W_2 = 0.34, W_3 = 0.71$.
采用实时采集的70个炉次的350000组的需量与功率数据对本文所提需量多步预报算法与文献[9]多步预报算法进行了预报步数$ i = 1, \cdots, 10 $的对比实验. 采用文献[23]的均方根误差(Root mean square error, RMSE)式(28), 文献[24]的拟合优度$ R^2 $式(29), 文献[17]的平均绝对百分比误差(Mean absolute percentage error, MAPE)式(30), 需量第$ i $步预报的上升趋势预报准确率$ {TPR}_i $式(25)和下降趋势预报准确率$ { TNR}_i $式(26)指标对本文所提需量多步预报算法和文献[9]多步预报算法的实验结果进行评估. 实验结果见表2.
表 2 需量预报精度对比Table 2 Precision comparison of demand forecast预报步数$i$ 1 2 3 4 5 6 7 8 9 10 $R^2_i\;(\%)$ 本文 99.96 99.62 99.59 99.47 99.39 99.31 98.99 98.51 98.03 97.95 文献[9] 90.34 90.05 89.77 89.54 88.73 88.48 88.01 87.76 87.33 86.94 ${{RMSE} }_i$ 本文 9.93 11.06 11.99 13.03 13.89 14.73 16.05 16.83 17.93 18.78 文献[9] 24.92 30.01 34.49 39.99 44.79 50.23 54.93 60.05 65.32 70.64 ${{MAPE} }_i\;(\%)$ 本文 0.04 0.05 0.05 0.06 0.06 0.07 0.07 0.08 0.08 0.08 文献[9] 0.11 0.13 0.15 0.18 0.20 0.22 0.24 0.27 0.29 0.32 $TPR_i\;(\%)$ 本文 94.88 93.21 92.19 91.42 90.17 89.77 88.21 90.05 91.55 89.66 文献[9] 86.12 82.11 80.05 80.11 78.94 79.33 79.11 77.06 80.15 79.02 $TNR_i\;(\%)$ 本文 93.22 94.67 92.19 92.01 94.21 93.18 90.96 89.99 88.12 90.01 文献[9] 81.12 80.04 80.67 83.72 79.99 80.15 77.56 86.77 80.15 76.91 $$ {{RMSE}}_i = \sqrt{\frac{1}{N_t}\sum\limits_{k = 1}^{N_t} \left( \bar{p}(k)-\hat{\bar{p}}_i(k)\right)^2} $$ (28) $$ { R}_i^2 = \frac{\sum\limits_{k = 1}\limits^{N_t}\left( \hat{\bar{p}}_i(k)-{\tilde{p}}_i\right)^2 }{\sum\limits_{k = 1}\limits^{N_t}\left(\bar{p}_i(k)-\tilde{p}_i \right)^2 }\times 100{\text{%}} $$ (29) 其中, $ \tilde{p}_i = \frac{1}{N_t}\sum_{k = 1}^{N_t} \bar{p}(k+i-1) $.
$$ {{MAPE}}_i = \frac{1}{N_t}\sum\limits_{k = 1}^{N_t}\left|\frac{\bar{p}(k)-\hat{\bar{p}}_i(k)}{\bar{p}(k)}\right|\times 100{\text{%}} $$ (30) 为了能清楚地对比实验结果, 采用图4 ~ 图6表示从在线的350000组数据的实验结果中随机抽取100组$ i = 1, 5, 10 $步需量预报结果, 虚线为本文需量预报结果, 实线为文献[9]需量预报结果, 点线为需量真实值. 可以看出本文需量预报方法与文献[9]方法相比, 预报精度明显提高.
从表2可以看出, 本文的方法与文献[9]方法的$ i = 1, 5, 10 $步预报结果相比, $ R^2 $提高$ 11.01{\text{%}} $, $ {{RMSE}}_i $降低51.86, $ {{MAPE}}_i $降低$ 0.24{\text{%}} $, 上升趋势$ { TPR}_i $提高$ 10.23{\text{%}} $, 下降趋势$ { TNR}_i $提高$ 14.22{\text{%}} $. 对比实验结果表明本文方法比文献[9]方法的需量多步预报精度和需量变化趋势的预报精度明显提高.
5. 结论
本文通过电熔镁砂生产过程熔化电流闭环控制系统方程建立需量动态模型, 在此基础上建立了由线性模型和未知非线性动态系统组成的需量多步预报模型, 采用文献[18]方法建立了未知非线性动态系统的自适应深度学习多步预报模型, 在此基础上提出了端边云协同的电熔镁砂生产过程需量多步智能预报方法. 采用70个炉次的电熔镁砂生产过程的实际数据的实验结果表明本文的方法与文献[9]方法的$ i = 1, 5, 10 $ 步预报结果相比, $ R^2 $提高$ 11.01{\text{%}} $, $ {{RMSE}}_i $降低51.86, $ {{MAPE}}_i $降低$ 0.24{\text{%}} $, 上升趋势$ { TPR}_i $提高$ 10.23{\text{%}} $, 下降趋势$ { TNR}_i $提高$ 14.22{\text{%}} $, 验证了本文所提的预报方法可以准确预报需量的变化趋势, 为实现需量尖峰的准确预报和控制创造了条件.
-
表 1 各种数据关联算法的比较
Table 1 Comparison of various data association algorithms
方法 优点 缺点 适用场景 NN/GNN 计算量小, 实时性较好, 工程实现简单 抗干扰能力弱, 在量测信息密度较大或环境因素过于复杂时, 性能较差 仅适用于信噪比较高, 目标密度较小的场合 PDA 计算量和存储量较小, 易于工程实现 在密集杂波或多目标环境中容易产生误跟或丢失等现象 适用于杂波环境下的单目标或跟踪门不重叠的多目标环境 JPDA 不需要任何关于目标和杂波的先验信息 计算量和存储量大, 实时性差, 工程实现困难, 量测数和目标数较大时存在组合爆炸现象 适用于密集多目标和多杂波、目标数目恒定已知的情况 MHT 在理想条件下是处理数据关联的最优算法 计算量大, 过于依赖目标和杂波的先验知识, 假设数量随量测数和目标数呈指数级增长 适用于密集多目标和多杂波、目标数未知且时变的情况 PMHT 批处理方法, 计算量随目标数的增长而呈线性增长 目标的后验概率函数可能会收敛到局部最大值, 算法对初始值比较敏感 适用于密集多目标和多杂波、目标数未知且时变的情况 
下载: 导出CSV
-
[1] 李双建, 徐从春. 论海洋的战略地位和现代海洋发展观. 经济研究导刊, 2012, (27): 256−259Li Shuang-Jian, Xu Cong-Chun. Discussion on the Ocean's strategic position and modern ocean development concept. Economic Research Guide, 2012, (27): 256−259 [2] 刘忠, 刘志坤, 罗亚松, 颜冰, 胡洪宁. 水下自组织网络及军事应用. 北京: 国防工业出版社, 2015. 8−10Liu Zhong, Liu Zhi-Kun, Luo Ya-Song, Yan Bing, Hu Hong-Ning. Underwater Self-Organizing Network and Military Applications. Beijing: National Defense Industry Press, 2015. 8−10 [3] 郭戈, 王兴凯, 徐慧朴. 基于声呐图像的水下目标检测、识别与跟踪研究综述. 控制与决策, 2018, 33(5): 906−922Guo Ge, Wang Xing-Kai, Xu Hui-Pu. Review on underwater target detection, recognition and tracking based on sonar image. Control and Decision, 2018, 33(5): 906−922 [4] Chen Z Y, Xu W. Joint passive detection and tracking of underwater acoustic target by beamforming-based Bernoulli filter with multiple arrays. Sensors, 2018, 18(11): 4022 doi: 10.3390/s18114022 [5] Sozer E M, Stojanovic M, Proakis J G. Underwater acoustic networks. IEEE Journal of Oceanic Engineering, 2000, 25(1): 72−83 doi: 10.1109/48.820738 [6] Ghafoor H, Noh Y. An overview of next-generation underwater target detection and tracking: An integrated underwater architecture. IEEE Access, 2019, 7: 98841−98853 doi: 10.1109/ACCESS.2019.2929932 [7] Isbitiren G, Akan O B. Three-dimensional underwater target tracking with acoustic sensor networks. IEEE Transactions on Vehicular Technology, 2011, 60(8): 3897−3906 doi: 10.1109/TVT.2011.2163538 [8] Luo J H, Han Y, Fan L Y. Underwater acoustic target tracking: A review. Sensors, 2018, 18(2): 112 doi: 10.3390/s18010112 [9] Luo H J, Wu K S, Ruby R, Liang Y Q, Guo Z W, Ni L M. Software-defined architectures and technologies for underwater wireless sensor networks: A survey. IEEE Communications Surveys & Tutorials, 2018, 20(4): 2855−2888 [10] Akyildiz I F, Pompili D, Melodia T. Underwater acoustic sensor networks: Research challenges. Ad Hoc Networks, 2005, 3(3): 257−279 doi: 10.1016/j.adhoc.2005.01.004 [11] Tuna G, Gungor V C. A survey on deployment techniques, localization algorithms, and research challenges for underwater acoustic sensor networks. International Journal of Communication Systems, 2017, 30(17): e3350 doi: 10.1002/dac.3350 [12] Akyildiz I F, Pompili D, Melodia T. Challenges for efficient communication in underwater acoustic sensor networks. ACM SIGBED Review, 2004, 1(2): 3−8 doi: 10.1145/1121776.1121779 [13] 李风华, 路艳国, 王海斌, 郭永刚, 张飞. 海底观测网的研究进展与发展趋势. 中国科学院院刊, 2019, 34(3): 321−330Li Feng-Hua, Lu Yan-Guo, Wang Hai-Bin, Guo Yong-Gang, Zhang Fei. Research progress and development trend of seafloor observation network. Bulletin of the Chinese Academy of Sciences, 2019, 34(3): 321−330 [14] O'Donnell J, Codiga D, Edwards C, Ullman D, Hebert D, Rice J, et al. Front Resolving Observational Network with Telemetry (FRONT). Connecticut Univ Groton Marine Sciences Inst, 2002 [15] 佟盛, 张信学. 美军水下网络中心战技术发展及设想. 舰船科学技术, 2009, 31(2): 155−159Tong Sheng, Zhang Xin-Xue. The technological development and imagine of US navy underwater network centric warfare. Ship Science and Technology, 2009, 31(2): 155−159 [16] Grund M, Freitag L, Preisig J, Ball K. The PLUSNet underwater communications system: Acoustic telemetry for undersea surveillance. In: Proceedings of OCEANS 2006. Boston, MA, USA: IEEE, 2006. 1−5 [17] Killeen T L. Ocean Observatories Initiative (OOI): Advanced research tools for the ocean sciences. Marine Technology Society Journal, 2010, 44(6): 15−17 doi: 10.4031/MTSJ.44.6.18 [18] 李建如, 许惠平. 加拿大“海王星” 海底观测网. 地球科学进展, 2011, 26(6): 656−661Li Jian-Ru, Xu Hui-Ping. NEPTUNE-Canada. Advances in Earth Science, 2011, 26(6): 656−661 [19] 申中寅. 日本海洋实时监测系统DONET简介. 国际地震动态, 2018, (7): 34−40Shen Zhong-Yin. A brief introduction to DONET in Japan. Recent Developments in World Seismology, 2018, (7): 34−40 [20] Person R, Miranda J M, Puillat I. ESONIM − European seafloor observatory network implementation model. Esonews, 2008, 1(3): 1−8 [21] 杨丽坤. 海洋强国战略的顶层设计研究. 大连海事大学学报(社会科学版), 2015, 14(2): 73−77Yang Li-Kun. The top-level design research of the strategy of maritime power. Journal of Dalian Maritime University (Social Science Edition), 2015, 14(2): 73−77 [22] 国务院关于印发国家重大科技基础设施建设中长期规划(2012−2030年). 中国科技投资, 2013, (7): 9State Council's plan for issuing national mid- and long-term plans for the construction of major science and technology infrastructure (2012−2030). China Venture Capital, 2013, (7): 9 [23] 房建孟. 全国海洋观测网规划(2014−2020年). 中国海洋年鉴, 2015. 41−46Fang Jian-Meng. National Marine observation network planning (2014−2020). China Marine Yearbook, 2015. 41−46 [24] 许惠平, 张艳伟, 徐昌伟, 李建如, 刘丁, 覃如府, 等. 东海海底观测小衢山试验站. 科学通报, 2011, 56(22): 1839−1845 doi: 10.1360/csb2011-56-22-1839Xu Hui-Ping, Zhang Yan-Wei, Xu Chang-Wei, Li Jian-Ru, Liu Ding, Qin Ru-Fu, et al. Coastal seafloor observatory at Xiaoqushan in the East China Sea. Chinese Science Bulletin, 2011, 56(22): 1839−1845 doi: 10.1360/csb2011-56-22-1839 [25] 彭晓彤, 周怀阳, 吴邦春, 吕枫, 吴正伟, 杨灿军, 等. 美国MARS海底观测网络中国节点试验. 地球科学进展, 2011, 26(9): 991−996Peng Xiao-Tong, Zhou Huai-Yang, Wu Bang-Chun, Lv Feng, Wu Zheng-Wei, Yang Can-Jun, et al. Test China node on monterey accelerated research system (MARS). Advances in Earth Sciences, 2011, 26(9): 991−996 [26] 《声学技术》编辑部. 中国科学院声学研究所首次实现我国深海潜标数据无线实时传输. 声学技术, 2017, (1): 87Editorial Department of “Acoustics Technology”. The institute of acoustics of the Chinese Academy of Sciences has realized the wireless real-time transmission of deep-sea submersible data for the first time. Technical Acoustics, 2017, (1): 87 [27] 央视新闻客户端. 我国将建国家海底科学观测网总投资超20亿元. 科技传播, 2017, 9(11): 8CCTV News Client. China will build a national seabed science observation network with a total investment of more than 2 billion Yuan. Public Communication of Science & Technology, 2017, 9(11): 8 [28] Teymorian A Y, Cheng W, Ma L R, Cheng X Z, Lu X C, Lu Z X. 3D underwater sensor network localization. IEEE Transactions on Mobile Computing, 2009, 8(12): 1610−1621 doi: 10.1109/TMC.2009.80 [29] Lin W L, Li D S, Tan Y, Chen J, Sun T. Architecture of underwater acoustic sensor networks: A survey. In: Proceedings of the 2008 1st International Conference on Intelligent Networks and Intelligent Systems. Wuhan, China: IEEE, 2008. 155−159 [30] 陈华炎. 基于水下无线传感器网络的高能效目标跟踪研究[博士学位论文], 浙江大学, 中国, 2018Chen Hua-Yan. Energy-Efficient Target Tracking based on UWSNs [Ph. D. dissertation], Zhejiang University, China, 2018 [31] Li L, Qiao G X, Zhao J, Yang L J, Imtiaz M N. Design of communication node in underwater acoustic network. In: Proceedings of the 2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer (MEC). Shengyang, China: IEEE, 2013. 591−594 [32] Maqsood H, Javaid N, Yahya A, Ali B, Khan Z A, Qasim U. MobiL-AUV: AUV-aided localization scheme for underwater wireless sensor networks. In: Proceedings of the 10th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS-2016). Fukuoka, Japan: IEEE, 2016. 170−175 [33] Gong Z J, Li C, Jiang F. AUV-aided joint localization and time synchronization for underwater acoustic sensor networks. IEEE Signal Processing Letters, 2018, 25(4): 477−481 doi: 10.1109/LSP.2018.2799699 [34] Yang H M, Sikdar B. A mobility based architecture for underwater acoustic sensor networks. In: Proceedings of the 2008 IEEE Global Telecommunications Conference. New Orleans, LO, USA: IEEE, 2008. 1−5 [35] Lin Y, Tao H X, Tu Y, Liu T. A node self-localization algorithm with a mobile anchor node in underwater acoustic sensor networks. IEEE Access, 2019, 7: 43773−43780 doi: 10.1109/ACCESS.2019.2904725 [36] 黎作鹏, 蔡绍滨, 张菁, 高振国, 赵靖. 水声传感器网络节点定位技术综述. 小型微型计算机系统, 2012, 33(3): 442−447Li Zuo-Peng, Cai Shao-Bin, Zhang Jing, Gao Zhen-Guo, Zhao Jing. Survey on node localization technology of underwater acoustic sensor networks. Journal of Chinese Computer Systems, 2012, 33(3): 442−447 [37] 周宏仁, 敬忠良, 王培德. 机动目标跟踪. 北京: 国防工业出版社, 1991. 12−13Zhou Hong-Ren, Jing Zhong-Liang, Wang Pei-De. Tracking of Maneuvering Targets. Beijing: National Defense Industry Press, 1991. 12−13 [38] Singer R A. Estimating optimal tracking filter performance for manned maneuvering targets. IEEE Transactions on Aerospace & Electronic Systems, 1970, AES-6(4): 473−483 [39] Moose R L. An adaptive state estimation solution to the maneuvering target problem. IEEE Transactions on Automatic Control, 1975, 20(3): 359−362 doi: 10.1109/TAC.1975.1100961 [40] 周宏仁. 机动目标“当前”统计模型与自适应跟踪算法. 航空学报, 1983, 4(1): 73−86Zhou Hong-Ren. A “Current” statistical model and adaptive tracking algorithm for maneuvering targets. Acta Aeronautica et Astronautica Sinica, 1983, 4(1): 73−86 [41] Mehrotra K, Mahapatra P R. A jerk model for tracking highly maneuvering targets. IEEE Transactions on Aerospace and Electronic Systems, 1997, 33(4): 1094−1105 doi: 10.1109/7.624345 [42] Blom H A P, Bar-Shalom Y. The interacting multiple model algorithm for systems with Markovian switching coefficients. IEEE Transactions on Automatic Control, 1988, 33(8): 780−783 doi: 10.1109/9.1299 [43] 党建武. 水下多目标跟踪理论. 西安: 西北工业大学出版社, 2009. 38−43Dang Jian-Wu. Underwater Multi-target Tracking. Xi＇ an: Northwestern Polytechnical University Press, 2009. 38−43 [44] Xu J, Xu M Z, Zhou X Y. The bearing only target tracking of UUV based on cubature Kalman filter with noise estimator. In: Proceedings of the 36th Chinese Control Conference. Dalian, China, 2017. 5288−5293 [45] Wang X, Xu M X, Wang H B, Wu Y. Combination of interacting multiple models with the particle filter for three-dimensional target tracking in underwater wireless sensor networks. Mathematical Problems in Engineering, 2012, 2012: Article ID 829451 [46] Zhang J X, Liu M Q, Fan Z. Classify motion model via SVM to track underwater maneuvering target. In: Proceedings of the 2019 IEEE International Conference on Signal Processing, Communications and Computing. Dalian, China: IEEE, 2019. 1−6 [47] He C F, Wang Y Y, Chen C L, Guan X P. Target localization for a distributed SIMO sonar with an isogradient sound speed profile. IEEE Access, 2018, 6: 29770−29783 doi: 10.1109/ACCESS.2018.2843438 [48] Ramezani H, Jamali-Rad H, Leus G. Target localization and tracking for an isogradient sound speed profile. IEEE Transactions on Signal Processing, 2013, 61(6): 1434−1446 doi: 10.1109/TSP.2012.2235432 [49] 张铎. 基于水下无线传感器网络的自组织目标跟踪算法研究[博士学位论文], 浙江大学, 中国, 2019Zhang Duo. Self-Organizing Target Tracking based on UWSNs [Ph. D. dissertation], Zhejiang University, China, 2019 [50] Rao S K, Murthy K S L, Rajeswari K R. Data fusion for underwater target tracking. IET Radar, Sonar and Navigation, 2010, 4(4): 576−585 doi: 10.1049/iet-rsn.2008.0109 [51] Smith D, Singh S. Approaches to multisensor data fusion in target tracking: A survey. IEEE Transactions on Knowledge and Data Engineering, 2006, 18(12): 1696−1710 doi: 10.1109/TKDE.2006.183 [52] Luo R C, Yih C C, Su K L. Multisensor fusion and integration: Approaches, applications, and future research directions. IEEE Sensors Journal, 2002, 2(2): 107−119 doi: 10.1109/JSEN.2002.1000251 [53] Qiu J, Xing Z R, Zhu C S, Lu K F, He J L, Sun Y B, et al. Centralized fusion based on interacting multiple model and adaptive kalman filter for target tracking in underwater acoustic sensor networks. IEEE Access, 2019, 7: 25948−25958 doi: 10.1109/ACCESS.2019.2899012 [54] Hare J, Gupta S, Song J N. Distributed smart sensor scheduling for underwater target tracking. In: Proceedings of the 2014 Oceans. John's, NL, Canada: IEEE, 2014. 1−6 [55] Braca P, Goldhahn R, Ferri G, Lepage K D. Distributed information fusion in multistatic sensor networks for underwater surveillance. IEEE Sensors Journal, 2015, 16(11): 4003−4014 [56] Yu C H, Choi J W. Interacting multiple model filter-based distributed target tracking algorithm in underwater wireless sensor networks. International Journal of Control, Automation and Systems, 2014, 12(3): 618−627 doi: 10.1007/s12555-013-0238-y [57] Hare J Z, Gupta S, Song J N, Wettergren T A. Classification induced distributed sensor scheduling for energy-efficiency in underwater target tracking sensor networks. In: Proceedings of the 2017 Oceans. Anchorage, AK, USA: IEEE, 2017. 1−7 [58] 关欣, 何友, 衣晓. 带反馈信息的纯方位水下分布式融合算法. 系统仿真学报, 2003, 15(7): 947−949Guan Xin, He You, Yi Xiao. Bearings-only underwater distributed fusion algorithm with feedback information. Journal of System Simulation, 2003, 15(7): 947−949 [59] Han X Y, Liu M Q, Zhang S L, Zhang Q F. A multi-node cooperative bearing-only target passive tracking algorithm via UWSNs. IEEE Sensors Journal, 2019, 19(22): 10609−10623 doi: 10.1109/JSEN.2019.2931885 [60] Liu M Q, Zhao L J, Zhang S L. Delay-estimation-based asynchronous particle filtering for passive target tracking in underwater wireless sensor networks. In: Proceedings of the 36th Chinese Control Conference (CCC). Dalian, China: IEEE, 2017, 8929−8934 [61] 赵立佳. 基于水下传感网络异步量测的目标跟踪算法研究[硕士学位论文], 浙江大学, 中国, 2019Zhao Li-Jia. Target Tracking Algorithms based on Asynchronous Measurement of USNs [Master thesis], Zhejiang University, China, 2019 [62] Yan J, Zhang X N, Luo X Y, Sun Y L, Guan X P. AUV assisted asynchronous localization for underwater sensor networks. In: Proceeding of the 35th Chinese Control Conference (CCC). Chengdu, China: IEEE, 2016. 7291−7296 [63] Yan J, Zhang X N, Luo X Y, Wang Y Y, Chen C L, Guan X P. Asynchronous localization with mobility prediction for underwater acoustic sensor networks. IEEE Transactions on Vehicular Technology, 2018, 67(3): 2543−2556 doi: 10.1109/TVT.2017.2764265 [64] 朱光明. 异步水下传感器网络目标跟踪算法研究[博士学位论文], 浙江大学, 中国, 2015Zhu Guang-Ming. Research on Target Tracking Algorithms for Asynchronous Underwater Sensor Networks [Ph. D. dissertation], Zhejiang University, China, 2015 [65] Yan J, Zhao H Y, Pu B, Luo X Y, Chen C L, Guan X P. Energy-efficient target tracking with UASNs: A consensus-based Bayesian approach. IEEE Transactions on Automation Science and Engineering, 2020, 17(3): 1361−1375 [66] 薛锋, 刘忠, 曲毅. 基于Unscented粒子滤波的无序观测下水下无线传感器网络目标被动跟踪. 传感技术学报, 2007, 20(12): 2653−2658Xue Feng, Liu Zhong, Qu Yi. Target passive tracking based on unscented particle filter with out-of-sequence measurements in underwater wireless sensor networks. Chinese Journal of Sensors & Actuators, 2007, 20(12): 2653−2658 [67] Qiu W, Li L, Lei P Z, Wang Z L. Multiple targets tracking by using probability data association and cubature Kalman filter. In: Proceedings of the 10th International Conference on Wireless Communications and Signal Processing (WCSP). Hangzhou, China: IEEE, 2018. 1−5 [68] Qiu W, Wang W K, Zhuang Z Y, Lei P Z, Li L. Using ship radiated noise spectrum feature for data association in underwater target tracking. In: Proceedings of the 20th International Conference on Information Fusion (Fusion). Xi＇ an, China: IEEE, 2017. 1−5 [69] Yao Y, Zhao J H, Wu L N. Doppler data association scheme for multi-target tracking in an active sonar system. Sensors, 2019, 19(9): 2003 doi: 10.3390/s19092003 [70] Seget K, Schulz A, Heute U. Multi-hypothesis tracking and fusion techniques for multistatic active sonar systems. In: Proceedings of the 13th International Conference on Information Fusion. Edinburgh, UK: IEEE, 2010. 1−8 [71] Li X H, Willett P, Baum M, Li Y A. PMHT approach for underwater bearing-only multisensor−multitarget tracking in clutter. IEEE Journal of Oceanic Engineering, 2016, 41(4): 831−839 doi: 10.1109/JOE.2015.2506220 [72] Li X H, Li Y A, Yu J, Chen X, Dai M. PMHT approach for multi-target multi-sensor sonar tracking in clutter. Sensors, 2015, 15(11): 28177−28192 doi: 10.3390/s151128177 [73] Li X H, Zhao C X, Lu X F, Wei W. Underwater bearings-only multitarget tracking based on modified PMHT in dense-cluttered environment. IEEE Access, 2019, 7: 93678−93689 doi: 10.1109/ACCESS.2019.2927403 [74] 江同洋. 基于随机有限集的多目标贝叶斯滤波方法研究[博士学位论文], 浙江大学, 中国, 2015Jiang Tong-Yang. Multi-target Bayes Filtering based on Random Finite Sets [Ph. D. dissertation], Zhejiang University, China, 2015 [75] Mahler R P S. Multitarget Bayes filtering via first-order multitarget moments. IEEE Transactions on Aerospace and Electronic Systems, 2003, 39(4): 1152−1178 doi: 10.1109/TAES.2003.1261119 [76] Mahler R. PHD filters of higher order in target number. IEEE Transactions on Aerospace and Electronic Systems, 2007, 43(4): 1523−1543 doi: 10.1109/TAES.2007.4441756 [77] Melo J, Matos A. A PHD filter for tracking multiple AUVs. In: Proceedings of the 2014 Oceans. St. John's, NL, Canada: IEEE, 2014. 1−8 [78] Zhang S Z, Zhang X M, Yu Y. A forward-backward PHD smoother for tracking multiple AUVs. In: Proceedings of OCEANS. Shanghai, China: IEEE, 2016. 1−8 [79] Chen X, Li Y A, Li Y X, Yu J. PHD and CPHD algorithms based on a novel detection probability applied in an active sonar tracking system. Applied Sciences, 2018, 8(1): 36 [80] 王佰录. 基于随机集理论的分布式多传感器多目标跟踪技术研究[博士学位论文], 电子科技大学, 中国, 2018Wang Bai-Lu. Distributed Multi-Sensor Multi-Target Tracking in the Framework of Random Finite Sets [Ph. D. dissertation], University of Electronic Science and Technology, China, 2018 [81] Jing L Y, He C B, Huang J G, Ding Z. Energy management and power allocation for underwater acoustic sensor network. IEEE Sensors Journal, 2017, 17(19): 6451−6462 doi: 10.1109/JSEN.2017.2737229 [82] Yu C H, Lee K H, Choi J W, Seo Y B. Distributed single target tracking in underwater wireless sensor networks. In: Proceedings of the 2008 SICE Annual Conference. Tokyo, Japan: IEEE, 2008. 1351−1356 [83] Huang Y, Liang W, Yu H B, Xiao Y. Target tracking based on a distributed particle filter in underwater sensor networks. Wireless Communications and Mobile Computing, 2008, 8(8): 1023−1033 doi: 10.1002/wcm.660 [84] Hare J, Gupta S, Song J N. Distributed smart sensor scheduling for underwater target tracking. In: Proceedings of the 2014 Oceans. St. John's, NL, Canada: IEEE, 2014. 1−6 [85] Zhang Q, Zhang C J, Liu M Q, Zhang S L. Local node selection for target tracking based on underwater wireless sensor networks. International Journal of Systems Science, 2015, 46(16): 2918−2927 doi: 10.1080/00207721.2014.880199 [86] Sun Y L, Yuan Y Z, Li X L, Xu Q M, Guan X P. An adaptive sampling algorithm for target tracking in underwater wireless sensor networks. IEEE Access, 2018, 6: 68324−68336 doi: 10.1109/ACCESS.2018.2879536 [87] Zhang S L, Chen H Y, Liu M Q. Adaptive sensor scheduling for target tracking in underwater wireless sensor networks. In: Proceedings of the 2014 International Conference on Mechatronics and Control (ICMC). Jinzhou, China: IEEE, 2014. 55−60 [88] Chen H Y, Zhang S L, Liu M Q, Zhang Q F. An artificial measurements-based adaptive filter for energy-efficient target tracking via underwater wireless sensor networks. Sensors, 2017, 17(5): 971 doi: 10.3390/s17050971 [89] Zhang Q, Liu M Q, Zhang S L. Node topology effect on target tracking based on UWSNs using quantized measurements. IEEE Transactions on Cybernetics, 2015, 45(10): 2323−2335 doi: 10.1109/TCYB.2014.2371232 [90] Zhang S L, Chen H Y, Liu M Q, Zhang Q F. Optimal quantization scheme for data-efficient target tracking via UWSNs using quantized measurements. Sensors, 2017, 17(11): 2565 doi: 10.3390/s17112565 [91] Luo J H, Han Y, He X T. Optimal bit allocation for maneuvering target tracking in UWSNs with additive and multiplicative noise. Signal Processing, 2019, 164: 125−135 doi: 10.1016/j.sigpro.2019.06.005 [92] Zhang D, Liu M Q, Zhang S L, Fan Z, Zhang Q F. Mutual-information based weighted fusion for target tracking in underwater wireless sensor networks. Frontiers of Information Technology & Electronic Engineering, 2018, 19(4): 544−556 [93] Zhang D, Liu M Q, Zhang S L, Zhang Q F. Non-myopic energy allocation for target tracking in energy harvesting UWSNs. IEEE Sensors Journal, 2019, 19(10): 3772−3783 doi: 10.1109/JSEN.2018.2890078 [94] Han G J, Zhang C Y, Shu L, Rodrigues J J P C. Impacts of deployment strategies on localization performance in underwater acoustic sensor networks. IEEE Transactions on Industrial Electronics, 2015, 62(3): 1725−1733 doi: 10.1109/TIE.2014.2362731 [95] Zhang Q, Liu M Q, Zhang S L, Chen H Y. Node topology effect on target tracking based on underwater wireless sensor networks. In: Proceedings of the 17th International Conference on Information Fusion (FUSION). Salamanca, Spain: IEEE, 2014. 1−8 [96] Liu M Q, Zhang D, Zhang S L, Zhang Q F. Node depth adjustment based target tracking in UWSNs using improved harmony search. Sensors, 2017, 17(12): 2807 doi: 10.3390/s17122807 [97] Fariborzi H, Moghavvemi M. EAMTR: Energy aware multi-tree routing for wireless sensor networks. IET Communications, 2009, 3(5): 733−739 doi: 10.1049/iet-com.2008.0238 [98] Zhang R, Labrador M A. Energy-aware topology control in heterogeneous wireless multi-hop networks. In: Proceedings of the 2nd International Symposium on Wireless Pervasive Computing. San Juan, Puerto Rico: IEEE, 2007. 25−30 [99] Zeng D, Yan S F, Xu L J, Zhang Z. The low power DSP platform design of underwater acoustic communication system. In: Proceedings of the 2016 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC). Hong Kong, China: IEEE, 2016. 1−4 [100] Jiang P, Liu J, Wu F, Wang J Z, Xue A K. Node deployment algorithm for underwater sensor networks based on connected dominating set. Sensors, 2016, 16(3): 388 doi: 10.3390/s16030388 [101] Bouabdallah F, Zidi C, Boutaba R. Joint routing and energy management in underwater acoustic sensor networks. IEEE Transactions on Network and Service Management, 2017, 14(2): 456−471 doi: 10.1109/TNSM.2017.2679482 [102] Chen K Y, Ma M D, Cheng E, Yuan F, Su W. A survey on MAC protocols for underwater wireless sensor networks. IEEE Communications Surveys & Tutorials, 2014, 16(3): 1433−1447 期刊类型引用(7)
1. 张喜铭，徐欢，杨秋勇，高伟，张睿喆. 考虑电力系统数据治理智能化的数据库生成方法研究. 制造业自动化. 2024(02): 160-165+171 . 
百度学术2. 祝健杨，辛明勇，代奇迹. 基于深度神经网络的数字电网边缘侧数据迁移. 电子设计工程. 2024(08): 55-58+63 . 百度学术3. 张福胜，张扬，薛志胜，彭驰. 基于物联网的煤矿井下机电设备状态智能监测. 机械与电子. 2024(04): 45-49 . 百度学术4. 于秋玲，梁锦照，陈康平. 基于云边协同的交直流混联电网线路过负荷协调控制方法. 沈阳工业大学学报. 2024(03): 241-247 . 百度学术5. 陈琳，赵冬，尹建兵，王明昶，徐航. QoS数据不确定性下电力业务服务自适应选取模型. 电子设计工程. 2024(13): 131-134+139 . 百度学术6. 李远征，任潇，葛磊蛟，彭靖轩，徐秋实，李曦. 基于可逆固体氧化物电池的电氢耦合微电网全生命周期规划-运营研究. 中国电机工程学报. 2024(13): 5169-5185 . 百度学术7. 金义，宋永春，马路遥，曹雨，宋树，贺琳. 高维时序空间大数据关联特征精准挖掘算法. 电子设计工程. 2024(16): 161-165 . 百度学术其他类型引用(3)
-
下载:
计量
- 文章访问数: 2954
- HTML全文浏览量: 1763
- PDF下载量: 965
- 被引次数: 10
