Neural network-based flight control systems: Present and future

As the first review in this field, this paper presents an in-depth mathematical view of Intelligent Flight Control Systems (IFCSs), particularly those based on artificial neural networks. The rapid evolution of IFCSs in the last two decades in both the methodological and technical aspects necessitates a comprehensive view of them to better demonstrate the current stage and the crucial remaining steps towards developing a truly intelligent flight management unit. To this end, in this paper, we will provide a detailed mathematical view of Neural Network (NN)-based flight control systems and the challenging problems that still remain. The paper will cover both the model-based and model-free IFCSs. The model-based methods consist of the basic feedback error learning scheme, the pseudocontrol strategy, and the neural backstepping method. Besides, different approaches to analyze the closed-loop stability in IFCSs, their requirements, and their limitations will be discussed in detail. Various supplementary features, which can be integrated with a basic IFCS such as the fault-tolerance capability, the consideration of system constraints, and the combination of NNs with other robust and adaptive elements like disturbance observers, would be covered, as well. On the other hand, concerning model-free flight controllers, both the indirect and direct adaptive control systems including indirect adaptive control using NN-based system identification, the approximate dynamic programming using NN, and the reinforcement learning-based adaptive optimal control will be carefully addressed. Finally, by demonstrating a well-organized view of the current stage in the development of IFCSs, the challenging issues, which are critical to be addressed in the future, are thoroughly identified. As a result, this paper can be considered as a comprehensive road map for all researchers interested in the design and development of intelligent control systems, particularly in the field of aerospace applications.     

基于跨临界CO2热泵的茶叶生产能源系统负荷削减潜力

乡村产业中的化石能源设备逐渐被电能技术替代，引起了乡村负荷波动增大、部分时段产生集中高负荷的问题。为了解决以上问题，将低品位清洁能源应用至乡村的茶叶生产中，针对烘茶全过程的工艺要求提出了跨临界CO₂热泵烘茶技术；并以某茶叶生产乡村为对象，对其代表台区的全年日用电量及产茶日负荷进行了分析，得出采用CO₂热泵烘茶后其负荷得到大幅度削减，整体可降低至原负荷的39.6%~46.8%，峰值负荷与平时负荷的比值由原本的13.6降至5.4~6.2。跨临界CO₂热泵应用至农产品生产中可有效缓解乡村供电压力。     

基于TRNSYS的茯砖茶生产工艺能源系统节能环保特性研究

茯砖茶发酵、干燥过程中，烘房内温湿度稳定性和能源系统低能耗是保证茯砖茶品质与成本的重要因素。本文采用TRNSYS仿真与实验研究相结合的方法，对咸阳某茯砖茶厂实际使用的空气源热泵系统进行建模，通过研究各季节典型代表月烘房温湿度的波动情况，确定该空气源热泵系统在全年的运行状态是否满足工艺要求，在此基础上，对比了该系统在全年可运行季节代表月与该生产厂房早期使用的燃气锅炉系统的能耗仿真结果，对空气源热泵系统的节能与环保特性进行研究。结果表明：由于夏季送风质量流量过大且室外空气含湿量较高，7月烘房温湿度不满足工艺要求。热泵系统在1、4、10月的总标煤消耗量的平均值是锅炉系统的44.42%，平均CO2、SO2、NOx排放量分别为锅炉系统的34.13%、44.1%、40.60%。在茯砖茶发酵、干燥的过程中，相比于燃气锅炉系统，空气源热泵系统具有更好的节能与环保特性。     

Evaluation of cut cell cartesian method for simulation of a hook and claw type hydrogen pump

Hook and claw pumps are used for recirculation of excess hydrogen in fuel cells. Optimization of the pump design is essential. Computational Fluid Dynamic (CFD) is an effective method for performance optimization. However, it is difficult to conduct CFD simulation because of the sharp cusp of the rotor profile. Cut cell Cartesian mesh could be the solution to handle this complex and moving geometries. The aim of this paper is to evaluate ANSYS Forte for hook and claw pumps. Firstly, the conservation accuracy of the cut cell cartesian mesh is verified using an adiabatic piston cylinder case. Then, simulation results of hook and claw type pump are compared with experimental data. Finally, simulation results of air and hydrogen are compared. The results show that the CFD simulation of hook and claw pumps using cut cell cartesian mesh could provide an efficient and effective approach for the optimization of the system.     

A three-dimensional surface measurement system implemented with Gaussian process based adaptive sampling

Self-adaptive surface measurements that can reduce data redundancy and improve time efficiency are in high demand in many fields of science and technology. For this purpose, a system implemented with Gaussian process (GP) adaptive sampling is developed. The non-parametric GP model is applied to reconstruct the topography and guide the subsequent sampling position, which is determined from the inference uncertainty estimation. A criterion is proposed to terminate the GP adaptive measurement automatically without any prior model or data of the topography. Experiments on typical surfaces validate the intelligence, adaptability, and high accuracy of the GP method along with the stabilization of the automatic iteration termination. Compared with traditional raster sampling, data redundancy is reduced and the time efficiency is improved without sacrificing the surface reconstruction accuracy. The proposed method can be implemented in other systems with similar measurement principles, thus benefitting surface characterizations.     

环形通道内液态铅铋合金流动换热特性实验研究

通过对环形通道内液态铅铋合金的流动换热特性进行实验研究，得到了气泡泵注气对液态金属流动的影响，并拟合出环形通道内液态铅铋合金的摩擦系数关系式和换热特性关系式。结果表明：采用气泡泵注气能有效提升铅铋合金的质量流速；相同Reynolds数下环形通道内液态铅铋合金的摩擦系数大于由布拉休斯公式计算得到的摩擦系数；液态铅铋合金对流换热过程中，导热项占主导地位，并且Nusselt数随Peclet数的增大而增大。     

Biologically Inspired Design of Context-Aware Smart Products

The rapid development of information and communication technologies (ICTs) and cyber–physical systems (CPSs) has paved the way for the increasing popularity of smart products. Context-awareness is an important facet of product smartness. Unlike artifacts, various bio-systems are naturally characterized by their extraordinary context-awareness. Biologically inspired design (BID) is one of the most commonly employed design strategies. However, few studies have examined the BID of context-aware smart products to date. This paper presents a structured design framework to support the BID of context-aware smart products. The meaning of context-awareness is defined from the perspective of product design. The framework is developed based on the theoretical foundations of the situated function–behavior–structure ontology. A structured design process is prescribed to leverage various biological inspirations in order to support different conceptual design activities, such as problem formulation, structure reformulation, behavior reformulation, and function reformulation. Some existing design methods and emerging design tools are incorporated into the framework. A case study is presented to showcase how this framework can be followed to redesign a robot vacuum cleaner and make it more context-aware.     

基于PSO-ELM模型的潜油柱塞泵冲次优化方法

为改进油井后期泵效低下、能耗高等缺陷，提出了一种基于PSO-ELM模型的潜油柱塞泵冲次优化方法.采用粒子群（PSO）算法与极限学习机（ELM）相结合的方式来实现动液面软测量建模；根据动液面及潜油柱塞泵工作电流变化，以油井运行经济性最优为目的建立目标函数得到潜油柱塞泵冲次，解决了在油井生产时不能准确调节抽油机冲次问题；最后以目标函数关系建立模糊控制器模型，根据输入参数调整潜油柱塞泵冲次.实验结果表明，建立的软测量模型预测动液面精度高，模糊控制器能够更加合理地调整抽油机冲次，最终达到智能调整冲次大小、提高油井采油率及节能的目的.     

自然循环工况下离心泵阻力特性的实验研究与数值模拟

停转后泵的阻力特性对自然循环流量影响明显。为研究低流量自然循环工况下离心泵的阻力特性，设计了实验台架，对离心泵的正向压降、反向压降和损失系数进行了测量，实验雷诺数为2.0×10⁴～1.5×10⁵。实验表明：相同雷诺数下，反向压降明显高于正向压降；雷诺数大于8×10⁴时，损失系数基本保持不变，而低雷诺数下损失系数随雷诺数的降低有增大的趋势；基于实验得到了损失系数的经验关系式。采用CFD方法对离心泵的内部流场进行了模拟，计算表明：CFD方法能较好地预测损失系数，RNG k-ε模型与实验值的相对误差不超过10%；离心泵的压力损失主要集中在叶轮、导叶等结构的交界区域；正向与反向流动的流场分布存在显著区别；低雷诺数下局部流动更加不稳定。