Deterministic and probabilistic ship pitch prediction using a multi-predictor integration model based on hybrid data preprocessing,reinforcement learning and improved QRNN

The deterministic and probabilistic prediction of ship motion is important for safe navigation and stable real-time operational control of ships at sea. However, the volatility and randomness of ship motion, the non-adaptive nature of single predictors and the poor coverage of quantile regression pose serious challenges to uncertainty prediction, making research in this field limited. In this paper, a multi-predictor integration model based on hybrid data preprocessing, reinforcement learning and improved quantile regression neural network (QRNN) is proposed to explore the deterministic and probabilistic prediction of ship pitch motion. To validate the performance of the proposed multi-predictor integrated prediction model, an experimental study is conducted with three sets of actual ship longitudinal motions during sea trials in the South China Sea. The experimental results indicate that the root mean square errors (RMSEs) of the proposed model of deterministic prediction are 0.0254°, 0.0359°, and 0.0188°, respectively. Taking series #2 as an example, the prediction interval coverage probabilities (PICPs) of the proposed model of probability predictions at 90%, 95%, and 99% confidence levels (CLs) are 0.9400, 0.9800, and 1.0000, respectively. This study signifies that the proposed model can provide trusted deterministic predictions and can effectively quantify the uncertainty of ship pitch motion, which has the potential to provide practical support for ship early warning systems.     

基于推理注意力机制的二阶段网络图像修复

现有的图像修复方法在处理大面积缺失或高度纹理化的图像时，通常会产生扭曲的结构或与周围区域不一致的模糊纹理，无法重建合理的图像结构。为此，提出了一种基于推理注意力机制的二阶段网络图像修复方法。首先通过边缘生成网络生成合理的幻觉边缘信息，然后在图像补全网络完成图像的重建工作。为了进一步生成视觉效果更逼真的图像，提高图像修复的精确度，在图像补全网络采用推理注意力机制，有效控制了生成特征的不一致性，从而生成更有效的信息。所提方法在多个数据集上进行了实验验证，结果表明该图像修复方法的结构相似性指数达到了88.9%，峰值信噪比达到了25.56 dB，与现有的图像修复方法相比，该方法具有更高的图像修复精确度，生成的图像更逼真。     

基于概要数据结构的全网络持续流检测方法

持续流是隐蔽的网络攻击过程中显现的一种重要特征，它不产生大量流量且在较长周期内有规律地发生，给传统的检测方法带来极大挑战。针对网络攻击的隐蔽性、单监测点的重负荷和信息有限的问题，提出全网络持续流检测方法。首先，设计一种概要数据结构，并将其部署在每个监测点；其次，当网络流到达监测点时，提取流的概要信息并更新概要数据结构的一位；然后，在测量周期结束时，主监测点将来自其他监测点的概要信息进行综合；最后，提出流持续性的近似估计，通过一些简单计算为每个流构建一个位向量，利用概率统计方法估计流持续性，使用修正后的持续性估计检测持续流。通过真实的网络流量进行实验，结果表明，与长持续时间流检测算法（TLF）相比，所提方法的准确性提高了50%，误报率和漏报率分别降低了22%和20%，说明全网络持续流检测方法能够有效监测高速网络流量。     

Specific emitter identification for satellite communication using probabilistic neural networks

Electromagnetic signal emitted by satellite communication (satcom) transmitters are used to identify specific individual uplink satcom terminals sharing the common transponder in real environment, which is known as specific emitter identification (SEI) that allows for early indications and warning (I&W) of the targets carrying satcom furnishment and furthermore the real time electromagnetic situation awareness in military operations. In this paper, the authors are the first to propose the identification of specific transmitters of satcom by using probabilistic neural networks (PNN) to reach the goal of target recognition. We have been devoted to the examination by exploring the feasibility of utilizing the Hilbert transform to signal preprocessing, applying the discrete wavelet transform to feature extraction, and employing the PNN to perform the classification of stationary signals. There are a total of 1000 sampling time series with binary phase shift keying (BPSK) modulation originated by five types of satcom transmitters in the test. The established PNNs classifier implements the data testing and finally yields satisfactory accuracy at 8 dB(±1 dB) carrier to noise ratio, which indicates the feasibility of our method, and even the keen insight of its application in military.     

Analysis of the steady state probability distribution of a manufacturing system under the prioritised hedging point control policy

In order to evaluate the average production cost of a multi-product-type, multi-stage and multi-parallel-machine manufacturing system (denoted as mP/mS/mM), one of the effective ways is to obtain its steady-state probability distribution. Because the two-product-type and multi-parallel-machine system that demand backlog is not allowed can be considered as a basic building block of the mP/mS/mM system, we begin by investigating the method of obtaining its steady-state probability distribution under the prioritised hedging point control policy. Although the shape of the distribution domains of the work-in-process (WIP) levels influences the steady-state probability balance equations, we develop a unified form of the marginal probability balance equations for all the possible shapes of distribution domains, which can be used to calculate the marginal probability distribution for each product type for the two-product-type and multi-parallel-machine system. Furthermore, we extend this analysis method to both the multiple-product-type, multi-parallel-machine, and single-stage system and the more complex mP/mS/mM system, and propose a method to obtain their approximate marginal probability distributions of the WIP levels. Finally, numerical experiments are conducted to verify the accuracy of the proposed method of analysing the steady-state probability distribution of an mP/mS/mM system.     

Study of the influence of notch radii and temperature on the probability of failure: A methodology to perform a combined assessment

The fracture assessment of notched components based on cracked components approaches leads to over‐conservative failure predictions. In the research literature, several approaches are proposed to overcome this problem using an apparent fracture toughness, . Nevertheless, most of these approaches are based on deterministic assumptions despite the large and variable scatter exhibited by for different notch radii (ρ) or temperatures (T). This paper proposes a methodology for deriving a probabilistic field including the effect of temperature on the failure of notched components. First, the theory of critical distances is applied to transform each apparent fracture toughness into the equivalent fracture toughness for ρ = 0. Then, the temperature is supposed to act as a scale effect in the Weibull cumulative distribution function of the equivalent fracture toughness, and the corresponding scale effect function is derived. Finally, the applicability of the proposed methodology is illustrated by an example using two ferritic‐pearlitic steels: S275JR and S355J2.     

基于改进模糊有色Petri网的综合能源系统能耗动态过程模型及应用

针对综合能源系统在供能过程中的能耗动态特点,通过改进的Petri网方法,根据特定的建模规则,建立了一种基于改进模糊有色Petri网的综合能源系统能耗动态过程模型,并在Stateflow平台上利用实际算例进行了仿真分析。结果表明,所建模型合理、有效,有一定的分析计算特性和图形化表现能力,为进一步对系统需求侧规划和多能设备的合理匹配提供了理论基础和技术支持。     

Integration of imitation learning using GAIL and reinforcement learning using task-achievement rewards via probabilistic graphical model

The integration of reinforcement learning (RL) and imitation learning (IL) is an important problem that has long been studied in the field of intelligent robotics. RL optimizes policies to maximize the cumulative reward, whereas IL attempts to extract general knowledge about the trajectories demonstrated by experts, i.e, demonstrators. Because each has its own drawbacks, many methods combining them and compensating for each set of drawbacks have been explored thus far. However, many of these methods are heuristic and do not have a solid theoretical basis. This paper presents a new theory for integrating RL and IL by extending the probabilistic graphical model (PGM) framework for RL, control as inference. We develop a new PGM for RL with multiple types of rewards, called probabilistic graphical model for Markov decision processes with multiple optimality emissions (pMDP-MO). Furthermore, we demonstrate that the integrated learning method of RL and IL can be formulated as a probabilistic inference of policies on pMDP-MO by considering the discriminator in generative adversarial imitation learning (GAIL) as an additional optimality emission. We adapt the GAIL and task-achievement reward to our proposed framework, achieving significantly better performance than policies trained with baseline methods.