Clinical application of flexible ureteroscopic sheath with controllable intraluminal pressure in treating ureteral stones

Objective:The purpose of the study was to assess the clinical efficacy and safety of a combined perfusion suction platform with pressure feedback control function and an ureteroscopic suction sheath that can measure the ureteropelvic pressure in implementing lithotripsies.Methods:Fifty-two patients who underwent lithotripsy under intelligent monitoring of ureteral intraluminal pressure from June 2016 to January 2018 were retrospectively recruited.The inclusion standard was stone diameter>1.5 cm but<2.5 cm.After the 12/14 Fr suction sheath was placed,manometer interface and suction interface of the sheath were connected to the platform via the pressure sensor and suction tube,respectively.The ureteroscope was connected to the platform perfusion pump,and the crushed stones were aspirated out under negative pressure.Results:According to the location of the stone,21(40.4%)cases were classified as upper ureteral stones,19(36.5%)were midureteral stones,and 12(23.1%)were lower ureteral stones.Forty-seven patients underwent successful primary sheath placement and lithotripsy with a mean operative time of 34.5(standard deviation 18.3)min.Retrograde stone migration did not occur.There were eight patients with hematuria postoperatively.Serious complication was 1.9% with one case of ureteral perforation.Stone clearance was 95.7% at Day 1e2 postoperatively,and 100% at Day 30 postoperatively.Conclusion:Ureteroscopic lithotripsy with intelligent pressure control using our device improved the efficiency of the lithotripsy and rate of stone clearance.The safety of the operation can be ensured.It is worth popularization and application in clinical practice.

A review of artificial intelligence applications in high-speed railway systems

In recent years,the global surge of High-speed Railway(HSR)revolutionized ground transportation,providing secure,comfortable,and punctual services.The next-gen HSR,fueled by emerging services like video surveillance,emergency communication,and real-time scheduling,demands advanced capabilities in real-time perception,automated driving,and digitized services,which accelerate the integration and application of Artificial Intelligence(AI)in the HSR system.This paper first provides a brief overview of AI,covering its origin,evolution,and breakthrough applications.A comprehensive review is then given regarding the most advanced AI technologies and applications in three macro application domains of the HSR system:mechanical manufacturing and electrical control,communication and signal control,and transportation management.The literature is categorized and compared across nine application directions labeled as intelligent manufacturing of trains and key components,forecast of railroad maintenance,optimization of energy consumption in railroads and trains,communication security,communication dependability,channel modeling and estimation,passenger scheduling,traffic flow forecasting,high-speed railway smart platform.Finally,challenges associated with the application of AI are discussed,offering insights for future research directions.

Pressure control of PEMFC distributed power generator

Control design is important for PEMFC （proton exchange membrane fuel cell） distributed power generator to satisfy user requirement for safe and stable operation. For a complex multi-variable dynamic system, a dynamic simulation model is first established. In view of close coupling and non-linear relationships between variables, the intelligent auto-adapted PI decoupling control method is used. From the simulation results it is found that, by bringing quadratic performance index in the single neuron, constructing adaptive PI controller, and adjusting gas flow rates through the second pressure relief valve and air compressor coordinately, both anode and cathode pressures can be maintained at ideal levels.

INTELLIGENT INTEGRATION CONTROL OF ROTATING DISK VIBRATION

The rotating disk is a basic machine part that is u sed widely in industry. The motion equation is transformed into the dynamic equa tion in real modal space. The personating intelligent integration is introduced to improve the existing control method. These modes that affect the transverse vibration mainly are included to simulate the vibration of rotating disk, and two methods are applied separately on condition that the sensor and the ac tuator are collocated and non collocated. The results obtained by all sided si mulations show that the new method can obtain better control effect, especially when the sensor and the actuator are non collocated.

e-Automation,an Architecture for Distributed Industrial Automation Systems

Due to the complexity of modern industrial systems, a conventional automation system is not capable of providing sufficient information management and high-level intelligent approaches, as achieving these functionalities requires the support of comprehensive data management and coordination between system devices and heterogenous information. This paper proposes the concept of e-Automation, in which computer networking and distributed intelligence agent technologies are applied to industrial automation systems, and presents a hardware and software architecture that implements this concept. An open infrastructure based on multi-agent systems is employed in the proposed architecture of e-Automation, which aims to allow the implementation of diverse tasks and to permit greater configurability than can be obtained from a traditional system. To evaluate our proposed e-Automation concept, this paper presents a case study of substation information management which adopts the proposed e-Automation architecture in power system domain.

Grid Interconnection of Wind Energy System at Distribu-tion Level Using Intelligence Controller

Wind generation is being increasingly connected at distribution level due to increasing load demand. Permanent magnet synchronous generator (PMSG) is connected to?the wind turbine directly. Through the full power control of AC-DC-AC converters, the electrical power is then connected to the power grid. The power conversion circuits are made up of generator-side three phase diode rectifiers, boost converter and the grid-side three bridges and four wire inverters. A boost converter is controlled through an intelligence controller to maintained DC power constant despite of Variable output of PMSG, the grid-connected operation is constructed using the hysteresis current control method. The inverter is controlled to perform following function 1) power converter to inject power generated from RES to the grid, and 2) shunt APF to compensate current unbalance, load current harmonics, load reactive power demand and load neutral current. The model is implemented in MATLAB/ Simulink using sim power system.

Equilibrating Pressure with Auto-Control Valve in Water Distribution Networks

This paper probes into the feasibility of equilibrating pressure of water distribution network through (using auto-control valves) in theory and in the economy. An optimal valve control model is designed to minimize the sum of squares of residual pressure in the network. Such an analog simulation has been performed on the year 2003 programming network of a certain littoral district in North China, through which this paper confirms that it is feasible to equilibrate pressure with auto-control valves in theory. The research work has brought about a discovery of applicable conditions of valves in economic feasibility, which avoids a great economic loss due to the wild use of auto-control valve. In addition, simulated annealing algorithm is applied to optimize valve settings and shown to identify global optimum or near-optimum.

A Multi-agent Architecture in CORBA Environment for Distributed Measurement System

The MACE - a Multi agent based distributed measurement architecture in CORBA environment used to develop intelligent distributed measurement system for remote control and monitoring of instruments over network such as Internet and Ethernet was proposed. The architecture is characterized by interoperability, collaboration and intelligence by means of CORBA and multi agent technologies. The architecture and exemplifies it by a common project was described.

煤矿防冲钻孔机器人全自主钻进系统关键技术

针对高地应力矿井钻孔卸压作业智能化程度低的技术难题,总结分析了国内外钻孔卸压技术和装备的研究现状,指出研发高性能、高可靠、高效率的防冲钻孔机器人全自主钻进系统是破解冲击地压防治难题的重要发展方向。为此,凝练了影响钻进系统性能的“孔位精准识别、钻具姿态精确感知、无线电磁随钻智能检测、钻具运行状态智能识别和钻进系统精确控制”五大关键技术,并给出了解决思路和方法。针对在复杂恶劣环境下卸压孔的精确识别问题,设计了融合图像尺寸调节和多阶段训练模式的卸压孔图像样本扩充SinGAN模型,引入多层特征融合优化的FasterRCNN,构建了基于改进SqueezeNet轻量级网络架构的孔位识别模型,以实现卸压孔位的准确快速识别;针对钻具姿态精确感知问题,提出了基于改进梯度下降法算法优化无迹卡尔曼滤波的惯性测量单元(Inertial Measurement Unit,IMU)初始对准方法,设计了多个IMU的空间阵列布局方式,研究了基于BP神经网络的钻具姿态误差补偿方法,旨在提高钻具姿态的解算精度,实现精准钻孔卸压;针对复杂地质环境下钻进工况的精确检测问题,搭建了煤矿井下随钻测量无线电磁传输系统架构,探讨了微弱电磁波信号自适应调制和随钻高速双向电磁传输技术原理,研究了孔底地质参数、几何参数和工程参数的测量原理和实现过程;针对钻进系统运行状态识别问题,构建了钻进信号时域、频域、时频域的多域特征和深度网络高级特征提取架构,提出了钻进系统关键零部件健康状态评估和故障诊断技术,构建了基于改进蝙蝠优化长短期记忆网络的卡钻风险因子预测模型,实现对卸压钻具卡钻状态的准确预测;针对钻进系统的精确控制问题,分析了钻进系统的液压系统工作原理,构建了考虑煤岩性状的钻进系统精确控制方案,探讨了基于转矩和位置的钻进系统最优控制参数求解原理,旨在实现钻进回转系统和给进系统的智能协同控制和并行作业。

采场全生命周期的矿压危害事件知识图谱表示方法研究

知识图谱是认知智能研究不可或缺的组成部分。针对采场矿压危害事件传统分析方法对煤矿开采过程中应力时空演化过程及隐患演化与风险防控关系等表达存在不足的问题,本文基于采场全生命周期提出一种采场矿压危害事件知识图谱表示方法:首先,从地质灾害的角度,分析采场应力及分布的动态特性,对矿压地质灾害中的各节点进行动态关联,提出顾及时空过程的采场矿压地质灾害知识图谱表示方法。其次,从事故的角度,分析采场矿压事故隐患演化与风险防控过程,将隐患耦合演化与防治措施融入知识图谱表示模型中。最后,运用Neo4j构建矿压危害事件知识图谱。结果表明:依据该表示方法构建的知识图谱,不仅刻画了灾害事件中不同对象的时空演化过程,还描述了隐患耦合演化过程以及对应的风险防控措施,为采场矿压危害的防治提供了智能研究途径。

城市智慧排水管控中多元监测体系构建研究

城市河流与排水管网污染溯源的时效性差与监测体系空间覆盖不平衡等仍是城市水环境管理的突出问题。随着无人机、物联网、水质在线监测、高精度定位等技术的发展,实现快速污染溯源的多元监测体系正逐步实现。该研究通过对中山市濠头涌区域的排水管网关键节点与河流关键断面安装分布式检测仪表,并应用无人监测船对城市河流进行地形测量、水质监测,完成了监测体系的构建和多元监测数据的获取,实现了分布式仪表与无人监测船的优势互补。此外,基于电导率与氨氮相关性系数大于0.92的结果及氨氮作为主要污染物的现状,验证了电导率作为主要水质实时监测指标的合理性。

基于分布式协同控制技术的分散式无功补偿技术方案研究

结合实际工程的应用实例从分散式无功补偿方案的提出、分布式协同吸收方案的理论、具体工程方案的设计进行简单的论述。结合线路开通后的实际运行工况,利用设置于正线的能量回馈吸收装置实现了分散式无功补偿,该方案可减少或完全取消设置于主变电所侧的SVG容量,充分开发和利用了能馈吸收装置的能力,节约了工程投资,实现了既定设计目标。

基于异构多智能体自注意力网络的路网信号协调顺序优化方法

针对路网交通信号控制的复杂性,本文提出基于异构多智能体自注意力网络的路网信号协调顺序优化方法,提升路网范围内多交叉口信号控制策略性能。首先,模型考虑多交叉口交通流的空间相关性,采用基于自注意力机制的价值编码器学习交通观测表征,实现路网级通信;其次,面向多智能体策略更新的非稳态环境,模型在前序智能体的联合动作基础上,基于多智能体优势分解的策略解码器,顺序决策最优反应动作;最后,设计基于有效行驶车辆的动作掩码机制,在时效完备区间自适应调节决策频率,并提出考虑等待公平性的时空压力奖励函数,进一步提高策略性能与实用性。在杭州路网数据集上验证模型有效性,结果表明:所提模型在2个数据集和5个性能指标上均优于基准模型;相比最优基准模型,所提模型平均行程时间降低10.89%,平均排队长度降低18.84%,平均等待时间降低22.21%。此外,所提模型的泛化能力更强,且显著减少车辆等待时间过长的情形。

船舶iCER系统除雾器模拟计算与性能优化

为了得到折流板除雾器的最优运行工况,并对除雾器进行优化改进,基于智能废气再循环(iCER)系统除雾需求,选择2种转折角度(120°和135°)的除雾器进行模拟计算,分析转折角度、液滴速度和液滴粒径等3种因素对除雾效率和压降的影响,结果表明:液滴粒径越大,除雾器的除雾效果越好;液滴速度越大,除雾器的除雾效果越好;转折角度为120°的除雾器相比转折角度为135°的除雾器除雾效果更好,但压降更大。研究除雾器的优缺点,设计一种带半圆板的新型除雾器,试验结果证明其具有高效率、低压降的特点,是一种符合iCER系统试验要求的除雾器。

智能化分布式指挥与控制建设及关键技术应用

为厘清智能化分布式指挥与控制体系的发展态势及其关键技术,基于系统工程思维,通过收集开源情报、整合体系架构与建设进展等方式,对美军典型案例进行深入研究。同时,对其在特定作战场景中的应用进行阐释。结果表明,面向未来大规模、快节奏、多样化的战争,美军通过构建联合战术网、布局无人控制平台、研发智能决策辅助系统的方式增强作战指挥与控制的智能性。通过具体案例分析可知,分布式指挥与控制的智能化主要依赖边缘云、人工智能、无人自主系统及先进网络通信等关键技术。

柔性力感知电子织物的制备及其人体运动监测系统构建

为开发步态失稳监测系统和压疮监测与预防床垫等老龄健康维护产品,研发了一种用于人体运动监测的柔性压阻式压力传感电子织物,2个电极层织物通过正交配置形成传感点阵,由石墨烯与离子液体改性处理的棉织物构成中间导电层。实验结果表明:该电子织物在0~5 kPa压力范围的传感灵敏度为0.15 kPa^(-1),且呈现良好的线性关系,加载、卸载时具有快速响应时间(20、30 ms),经校准实验所得压力映射图呈现良好均匀性,传感性能可重复8000次循环。将自主设计的上位机软件、下位机电路等集成智能电子织物压力分布监测系统,可达成对不同身体部位的压力大小及其分布情况的实时连续监测,未来可用于步态分析、压疮监测与预防床垫、人体运动特征等辨识。

厂区级冷却供水系统智能控制设计实现

某厂区冷却供水系统只能以手动模式运行,无法实现自动恒压供水,能耗高、设备损耗大,对管网流量波动适应性差;通过重新设计系统PLC程序,进行加减泵逻辑控制和管网压力设置,实现了基于变频器的管网恒压控制;通过水泵轮巡逻辑控制和冗余配置,实现了水泵的自动轮换运行;通过水泵使能功能和管网压力手动设置功能,提高了系统控制的灵活性;通过优化水泵加载条件和触摸屏功能,消除了设备故障对系统自动运行的干扰;经过10个月运行验证,系统一直稳定工作,水泵运行数量减少三分之一,管网运行压力降低12.8%,可设置参数由3个增加到15个,冷却供水泵组节能23%以上。

伴上尿路结石的尿源性脓毒血症患者引流后早期或晚期行智能控压软镜碎石术的有效性和安全性

目的比较伴上尿路结石的尿源性脓毒血症患者引流后早期或晚期行智能控压软镜碎石术治疗的安全性和有效性。方法回顾性分析2022年5月—2023年5月于南通大学附属医院泌尿外科行智能控压软镜碎石术治疗的59例伴上尿路结石的尿源性脓毒血症患者的临床资料,根据一期引流减压至二期碎石治疗间隔时间分为早期碎石(≤1周)组(n=27)与晚期碎石(>1周)组(n=32),比较两组患者的基线资料、影像学资料、术中及术后资料。结果两组患者在结石清除率、总并发症发生率、高级别并发症发生率、碎石治疗后的住院时间、碎石治疗后的住院费用和总住院治疗费用方面比较,差异均无统计学意义(P>0.05)。结论采用智能控压软镜碎石术早期碎石(≤1周)和晚期碎石(>1周)治疗尿源性脓毒血症引流后的患者均安全有效。

基于RBF神经网络的进气压力控制方法研究

针对高空台进气压力控制系统的强非线性特性和被控对象难以精确建模的问题,传统的PID控制在被试发动机进行加减速等过渡态时难以满足进气压力控制性能要求,提出了基于数据驱动的高空台压力控制方法,设计了基于RBF(Radial Basis Function,径向基函数)神经网络的最优控制架构,通过分析进气压力控制系统的输入和输出,给出了进气压力控制系统的RBF神经网络控制方法;利用高空台的大量试验数据对所设计的控制方法进行了训练和测试。测试结果表明,所设计的智能控制方法有良好的控制性能,能够满足进气压力的过渡态自适应控制。

带有扰动观测器的智能车队分布式协同控制

目的为了研究含有未知外部扰动和未知非线性项的领航车辆和跟随车辆的同质车队控制问题,实现车队协同控制并达到车队控制目标,以解决交通拥堵、减少尾气排放和提高道路交通容量。方法本文提出一种新的分布式车队协同滑模控制策略,结合车辆间距策略和通信拓扑结构,确保车队的稳定性以及间距误差和速度误差的收敛性。针对车辆动力学模型中的未知非线性项,提出分布式神经网络自适应律,用于估计和补偿系统中未知非线性项的影响。并且,由于车队系统不可避免地会受到外部扰动的影响,设计扰动观测器并调整其参数,以逼近系统的实际外部扰动。结果通过Lyapunov稳定性分析证明分布式车队控制策略的正确性和有效性,并通过相应的车队控制实例进行验证。结论所提出的分布式协同滑模控制策略和分布式神经网络自适应律能够有效实现车队协同,保证系统的快速响应、稳定性和鲁棒性。