A study on temperature monitoring method for inverter IGBT based on memory recurrent neural network

The power module of the Insulated Gate Bipolar Transistor(IGBT)is the core component of the traction transmission system of high-speed trains.The module's junction temperature is a critical factor in determining device reliability.Existing temperature monitoring methods based on the electro-thermal coupling model have limitations,such as ignoring device interactions and high computational complexity.To address these issues,an analysis of the parameters influencing IGBT failure is conducted,and a temperature monitoring method based on the Macro-Micro Attention Long Short-Term Memory(MMALSTM)recursive neural network is proposed,which takes the forward voltage drop and collector current as features.Compared with the traditional electricalthermal coupling model method,it requires fewer monitoring parameters and eliminates the complex loss calculation and equivalent thermal resistance network establishment process.The simulation model of a highspeed train traction system has been established to explore the accuracy and efficiency of MMALSTM-based prediction methods for IGBT power module junction temperature.The simulation outcomes,which deviate only 3.2% from the theoretical calculation results of the electric-thermal coupling model,confirm the reliability of this approach for predicting the temperature of IGBT power modules.

Wearable Smart Sensor System for Medical Monitoring with an Assessment of the Level of Blood Loss and Pain Shock Because of Trauma or Injury

Blood loss in peacetime is mainly due to the normal menstrual cycle in women or diseases with surgical intervention. In wartime, blood loss in military personnel is a characteristic sign of a closed or open injury of the body during internal or external bleeding. Access to clinical care for wounded military personnel injured on the battlefield is limited and has long delays compared to patients in peacetime. Most of the deaths of wounded military personnel on the battlefield occur within the first hour after being wounded. The most common causes are delay in providing medical care, loss of time for diagnosis, delay in stabilization of pain shock and large blood loss. Some help in overcoming these problems is provided by the data in the individual capsule, which each soldier of the modern army possesses;however, data in an individual capsule is not sufficient to provide emergency medical care in field and hospital conditions. This paper considers a project for development of a smart real-time monitoring wearable system for blood loss and level of shock stress in wounded persons on the battlefield, which provides medical staff in field and hospital conditions with the necessary information to give timely medical care. Although the hospital will require additional information, the basic information about the victims will already be known before he enters the hospital. It is important to emphasize that the key term in this approach is monitoring. It is tracking, and not a one-time measurement of indicators, that is crucial in a valid definition of bleeding.

A New Software for GIS Image Pixel Topographic Fac－tors in Remote Sensing Monitoring of Soil Losses

ＡＮｅｗＳｏｆｔｗａｒｅｆｏｒＧＩＳＩｍａｇｅＰｉｘｅｌＴｏｐｏｇｒａｐｈｉｃＦａｃ－ｔｏｒｓｉｎＲｅｍｏｔｅＳｅｎｓｉｎｇＭｏｎｉｔｏｒｉｎｇｏｆＳｏｉｌＬｏｓｓｅｓＴＡＮＧＷＡＮ－ＬＯＮＧａｎｄＢＵＺＨＡＯ－ＨＯＮＧＩｎｓｔｉｔｕｔｅｏｆＳｏｉｌ...

A real-time beam loss monitoring system for storage ring of SSRF

In this paper we report the real-time beam loss monitoring (BLM) system at the storage ring of SSRF.The BLM-XS detectors and Ethernet data acquisition system are used in this system.Some applications and experiments of the BLM system are also presented.The BLM system provides dynamic information of beam loss for the storage ring,and is helpful to ensure the facility commissioning,investigate the problems of machine,optimize the machine parameters and further increase the beam lifetime.

Risk Assessment and Change Monitoring of Soil and Water Loss in Ruijin City Based on RS and GIS

The land use information extraction technology for the high-resolution remote sensing images of the Gaofen No. 1 satellite was construc-ted. According to the spectral, band, texture and shape attributes, land use types were divided, and the changing laws of land use types were ana- lyzed. Aftewards,according to the Table of Grading Standard of Sooil Erosion Intensity（SL190-96）,as well as vegetation coverage index NDVI slope, the risks of soil and water loss were assessed. Meanwhile, the level, scale, location and scope of changes in the risks of soil and water loss were monitored by using spatial visualization and spatial statistical techniques. The results showed that the area of areas without soil erosion and moderate soil erosion areas decreased obviously from 2015 to 2017, and the decreases were up to 22.929 3 and 13.626 3 km2 respectively. The ar-ea of mild soil erosion areas increased fast, and the increase reached 31.140 0 km2. The area of extremely strong soil erosion areas increased by 7.267 4 km2. In the city, moderate and strong soil erosion areas reduced, while extremely strong soil erosion patches increased fast, which was mainly related to road construction and construction and development of orchards. The extremely strong soil erosion areas were distributed in the shape of a banded loop, surrounded the suburbs of the city, and shrank towards the center of Ruijin City. The constructed technology to monitor the changes in land use and soil and water loss, as well as the changing laws of land use and soil and water loss provide the theoretical basis and plan-ning basis of soil and water conservation for urban planning departments and soil and water conservation departments.

Therapeutic drug monitoring in inflammatory bowel disease:The dawn of reactive monitoring

Inflammatory bowel disease(IBD)is a chronic condition that significantly affects the quality of life of its patients.Biologic drugs have been the mainstay treatment in the management of IBD patients but despite their significant contribution,there remains a proportion of patients that do not respond or lose response to treatment.Therapeutic drug monitoring(TDM)involves measuring levels of serum drug concentrations and anti-drug antibodies.TDM of biologic drugs initially emerged to understand treatment failure in other immune mediated inflammatory diseases.This was then introduced in IBD to rationalize primary non-response or secondary loss of response,given that low serum drug concentrations or the formation of anti-drug antibodies are variably associated with treatment failure.The aim of this narrative review is to provide an overview regarding the current use of TDM in clinical practice and to present the evidence available regarding its use in both proactive and reactive clinical settings in preventing and managing treatment failure.This review also presents the existing evidence regarding the association of various clinical outcomes with specific thresholds of drug concentrations,in everyday practice.A narrative review of published articles and conference abstracts regarding the use of TDM in IBD management,through an electronic search using PubMed and ScienceDirect.TDM has proven to be superior and more cost effective in guiding management of patients with treatment failure compared to empiric dose escalation or change in treatment.Despite a trend towards an association between clinical outcomes and drug concentrations,proactive TDM based strategies have not been shown to achieve clear benefit in long-term outcomes.In the clinical setting,TDM has proven to be useful in managing IBD patients,and its use in the reactive setting,as an additional tool to help manage patients with treatment failure,is being promoted as newer guidelines and consensus groups implement TDM as part of the management plan.

Cavity 3D modeling and correlative techniques based on cavity monitoring

According to the mining method for Dongguashan Copper Mine and Tongkeng Mine in China, and with the help of the cavity monitoring system(CMS) and mining software Surpac, the 3D cavity models were established exactly. A series of correlative techniques for calculating stope over-excavation and under-excavation, stope dilution and ore loss rates, and the blasting design of the pillar with complicated irregular boundaries were developed. These techniques were applied in Dongguashan Copper Mine and Tongkeng Mine successfully. Using these techniques, the dilution rates of stopes 52-2#, 52-6#, 52-8# and 52-10# of Dongguashan Copper Mine are calculated to be 2.12%, 8.46%, 12.67% and 10.68%, respectively, and the ore loss rates of stopes 52-6# and 52-8# are 4.41% and 3.70%, severally. Furthermore, according to the design accomplished by the technique for a pillar of Tongkeng Mine with irregular boundary, the volume, total length of boreholes and the dynamite quantity of the pillar are computed to be 1.2×104 m3, 2.98 km and 10.97 t, correspondingly.

Analysis and Application of the Synthetic Relative Measuring Method in On-Line Monitoring for Capacitive Equipment in Power Systems

On-line measurement for dielectric loss angle can effectively monitor the insulation condition of capacitive equipment in power systems. Synthetic relative measuring methods not only markedly overcome the shortcomings of traditional absolute measuring methods but also greatly improve the accuracy of dielectric loss angle measurement. However, synthetic relative measuring methods based on two or three pieces of capacitive equipment do not have the characteristic of generality. In this paper, a principle of synthetic relative measuring method is presented. The example of application for synthetic relative methods based on three and four pieces of capacitive equipment running in the same phase is taken to present the failure judgment matrices for N pieces of equipment. According to these matrices, the fault condition of N pieces of capacitive equipment can be watched, which is more general. Then some problems needing to be concerned along with two diagnostic methods used in diagnostic system are introduced. Finally, two programmable flow charts for the two methods are given and corresponding examples demonstrate their feasibility in practice.

Method to deploy wireless relays in industrial wireless monitoring

In light of demands for wireless monitoring and the characteristics of wireless channel,a complete deployment method containing channel survey,path loss estimation,and gradient grade of wireless relay nodes is proposed.It can be proved by experiments that under the premise of meeting the requirements of real-time and redundant-topology,the total number of relay nodes could be minimized by using the proposed method.

Study on the Determination of the Significant National Seismic Monitoring and Protection Regions

The paper describes firstly the principles and scientific train of thought involved in determining the significant seismic monitoring and protection regions (SSMPR) in China. The principles include the gradation principle, i.e. the national level SSMPR and the provincial level SSMPR, the principle of highlighting priorities, namely, the area of an SSMPR should be a fraction of the total area of the country or of the respective province, but the earthquake losses incurred in SSMPR should be a major proportion of the national or provincial ones. The scientific train of thought adopted is to determine the SSMPR on the basis of seismic hazard assessment and loss estimation. Secondly, it reviews the achievements in determining the SSMPRs for the period from 1996 to 2005. The result shows that 10 strong earthquakes occurred during that period in the areas with earthquake monitoring and prediction capability available on the Chinese continent, 8 of which occurred in SSMPRs with the economic loss and death toll accounting for 67% and 92% of the total loss on the Chinese mainland. Lastly, the paper introduces preparatory research for determining the SSMPR for the period from 2006 to 2020, including decade-scale mid-and long-range seismic risk assessment based on seismology, seismogeology, geodesy, earthquake engineering, sociology and stochastics and so on, and the national seismic risk probability map, the seismic hazard (intensity) map, earthquake disaster losses map and the comprehensive seismic risk index, etc. obtained for the period of 2006 to 2020.

基于缩尺模型的高铁桥梁预应力损失试验研究

【目的】为更好的评估在役预应力混凝土桥梁结构预应力损失状况。【方法】选用国内高铁中应用最广的32 m预应力混凝土箱梁作为研究对象,按照1:16的缩尺比例将箱梁转化为T形截面制作了26根C50混凝土试验模型梁。通过对试验梁预应力钢绞线应变、伸长量的瞬时和长期监测得到预应力损失的实际值,并将此实际值与目前国内外常用预应力损失规范计算所得值进行对比分析。【结果】预应力损失主要发生在前期即瞬时损失,约占总损失的70%;84.6%的试验梁锚固损失占瞬时损失总和的70%以上,最高达80.57%;试验梁的长期损失在锚固后的前10 d内变化较快,后期逐渐趋于稳定;将5种规范的计算结果与试验实测值进行对比,对于长期损失,数据显示实测数据与《铁路桥涵设计规范》(TB 10002—2017)计算结果最为吻合。【结论】研究结果可为实际工程中预应力梁的预应力损失计算提供参考。

基于改进PatchSVDD的田间异常区域检测方法

利用无人机遥感技术对农田进行监测并及时发现田间异常对保证农业生产具有重要意义。目前田间异常区域检测需要标注大量的正常与异常样本。然而,异常样本在整个农田区域中占比过小且无法充分收集。特别是农田异常的多样性和不可预知性,对检测方法的适用性提出了更高的要求。针对以上问题,本文提出基于改进PatchSVDD (Patch-level Support Vector Data Description)模型的田间异常区域检测方法,该方法仅使用田间正常区域的标注信息,即可对田间异常区域进行检测和定位。首先,改进方法引入不相邻图像块之间的边界损失函数,从而提升了正常与异常样本边界的判别性,改进了检测的鲁棒性;第二,引入外部记忆组件,通过压缩存储正常样本特征,从而在保证检测精度的基础上有效减少了测试阶段的时间和空间消耗;第三,构建了包含杂草簇、种植缺失、障碍物、双倍种植和积水共5个异常类型的田间异常数据集。本文方法在平均检测AUC(Area Under Curve)值和平均定位AUC值上分别达到了96.9%和94.6%,相比于原算法分别提升1.2%和1.6%,从而验证了方法的有效性。

电子监控部分遮挡目标单模态自监督信息挖掘技术

针对电子监控视频中受遮挡目标识别难度高的问题,提出一种电子监控部分遮挡目标单模态自监督信息挖掘技术。为了得到目标的状态信息,利用遮挡检测方法判断监控视频中是否存在部分遮挡目标。当监控视频存在部分遮挡目标时,利用减法聚类方法进行特定目标的识别、跟踪或描述,并提供更准确和详细的目标特征信息。在此基础上,将交叉熵损失函数与软间隔三元组损失函数构建的监督遮挡目标特征学习判别损失函数作为部分遮挡目标信息挖掘的目标函数,在每个批次的电子监控样本中,搜寻最小距离的负样本对以及最大距离的正样本对,并通过反向传播优化参数。由此输入电子监控图像样本,通过前向传播输出得到电子监控部分遮挡目标单模态自监督信息挖掘结果。实验结果表明,所提出的技术可以有效挖掘电子监控部分遮挡目标,目标挖掘的mAP值高于0.9,能够为提升监控目标识别精度提供可靠依据。

基于遥感技术的东北黑土区水土流失动态监测研究

东北黑土区是我国重要的商品粮基地,近年来面临水土流失严重、面积减小、土壤质量下降等问题,已成为目前土壤保护工作中亟待解决的重要问题。以东北黑土区2018年和2022年两期遥感影像与水土保持措施的实地调查数据作为数据源,利用目视识别法开展影像解译,并通过中国土壤流失方程CSLE进行土壤侵蚀模数的计算,对东北黑土区的水土流失变化情况及原因进行分析,结果表明:耕地、草地、建设用地、其他土地面积减少,园地、林地、交通运输用地、水域及水利设施用地面积增加,造林、种草、封育、地埂、水平阶/反坡梯田等面积共增加0.84万km^(2);对比2018—2022年东北黑土区的水土流失情况,整体呈向好趋势,土壤侵蚀面积共减少约1.01万km^(2);从侵蚀强度来看,除轻度侵蚀面积增加约0.45万km^(2)外,中度、强烈、极强烈、剧烈侵蚀面积分别减少约0.43万、0.24万、0.28万、0.51万km^(2);从不同省份侵蚀面积变化情况分析,内蒙古自治区东四盟的侵蚀面积减少最多,共减少约0.37万km^(2),辽宁省侵蚀面积变化最小,共减少约0.06万km^(2);耕地、建设用地等土地利用类型面积的减少,以及林地、交通运输用地等土地利用类型面积的增加,均可大幅减少土壤侵蚀面积,同时水土保持措施面积的增加也可有效阻止土壤侵蚀的发生。总体来看,东北黑土区水土流失治理效果显著,生态环境得到改善,持续进行东北黑土区水土流失治理对环境保护具有重要意义。

地下水封洞库施工期洞室围岩变形松弛典型特征与规律

基于地下水封洞库工程特征与典型洞库工程实例,整理分析大量洞室围岩内部变形、表层变形、波速与锚杆应力等监测数据.结果表明:预埋的多点位移计测点位移主要为0.5~3.0 mm,收敛位移监测值主要为4~8 mm,拱顶沉降监测值主要为3~6 mm,围岩时效变形不明显;围岩变形与爆破开挖有关,当掌子面或后续台阶开挖面接近监测断面时,变形出现陡增;围岩质量越差,开挖面空间效应越不明显.提出洞室围岩损失位移确定方法,发现损失位移占最终收敛位移50%~60%;基于波速变化率提出围岩松弛程度评价指标,发现围岩最大松弛程度约为0.47,松弛深度为1.5 m;洞室围岩锚杆受力普遍较小,锚杆拉应力与围岩变形基本同步变化.

基于边缘计算的实时线损监控系统研究

为有效减少数据传输量、降低服务响应时延、增强网络效能,设计了基于边缘计算的实时线损监控系统。系统通过分钟级数据进行小时级的台区线损计算。引入低压故指设备,对分支箱、表箱的进出线冻结电能进行测量,并对台区下各分段线损进行计算,以实现对台区的分级、分层线损的分析和管理。通过仿真与分析,线损计算应用(APP)能够实现实时线损数据计算及监控,计算所得线损率与用采系统中线损率基本一致。仿真结果验证了所提系统的有效性。

改进TDM-LoRa低功耗森林火灾监测预警系统

针对目前森林火灾监测系统成本高、功耗大、维护复杂的缺点,提出一种基于改进TDM-LoRa设计的低功耗森林火灾监测预警系统.系统以STM32系列微处理器为节点控制核心,LoRa-SX1278芯片为通信模块,并使用增量传输和改进时分复用通信机制,有效降低节点能耗,从而延长监测节点和汇聚节点寿命.试验结果表明,数据信息在发射功率为20 dBm、传输速率为1.2 kbit·s^(-1)的情况下,节点在3500 m范围内实现的丢包率仅为7.2%;在使用2600 mA·h的电池、数据采集上传间隔时间为30 min的情况下,单个节点有效工作时间理论可达90.7个月,实现无中继远距离低功耗森林环境监测数据的采集.

基于深度SSD改进模型的传动设备状态在线监测研究

针对现有传动设备在线监测算法存在的检测精度低、效率差等问题,提出一种基于改进SSD网络模型的在线检测算法;先对故障集进行预处理,通过滤波调制、共振解调等环节滤除原始故障集的噪声干扰;以VGG-16为基础设计了SSD网络结构,同时增加了辅助卷积层和预测层;对SSD网络模型进行改进,引入了注意力机制模块和特征增强模块,改善模型各层的数据共享性能同时提高了模型的数据训练效率;基于通道拼合方式对故障数据进行多尺度特征融合,并优化SSD模型的各层金字塔结构,以更好的匹配先验框及选择最佳的损失函数;实验结果显示,提出算法的传动设备故障检测率达到98.8%,参与对比的3种传统算法故障检测率分别为94.2%、93.6%和93.7%,同时提出算法的检测效率也优于传统算法。