Identification algorithm for a kind of fractional order system

The state-space representation of linear time-invariant (LTI) fractional order systems is introduced, and a proof of their stability theory is also given. Then an efficient identification algorithm is proposed for those fractional order systems. The basic idea of the algorithm is to compute fractional derivatives and the filter simultaneously, i.e., the filtered fractional derivatives can be obtained by computing them in one step, and then system identification can be fulfilled by the least square method. The instrumental variable method is also used in the identification of fractional order systems. In this way, even if there is colored noise in the systems, the unbiased estimation of the parameters can still be obtained. Finally an example of identifying a viscoelastic system is given to show the effectiveness of the aforementioned method.

Iterative identification of discrete-time output-error model with time delay

The problem of discrete-time model identification of industrial processes with time delay was investigated.An iterative and separable method is proposed to solve this problem,that is,the rational transfer function model parameters and time delay are alternately fixed to estimate each other.The instrumental variable technique is applied to guarantee consistent estimation against measurement noise.A noteworthy merit of the proposed method is that it can handle fractional time delay estimation,compared to existing methods commonly assuming that the time delay is an integer multiple of the sampling interval.The identifiability analysis for time delay is addressed and correspondingly,some guidelines are provided for practical implementation of the proposed method.Numerical and experimental examples are presented to illustrate the effectiveness of the proposed method.

Closed-loop identification of systems using hybrid Box–Jenkins structure and its application to PID tuning

The paper describes a closed-loop system identification procedure for hybrid continuous-time Box–Jenkins models and demonstrates how it can be used for IMC based PID controller tuning. An instrumental variable algorithm is used to identify hybrid continuous-time transfer function models of the Box–Jenkins form from discretetime prefiltered data, where the process model is a continuous-time transfer function, while the noise is represented as a discrete-time ARMA process. A novel penalized maximum-likelihood approach is used for estimating the discrete-time ARMA process and a circulatory noise elimination identification method is employed to estimate process model. The input–output data of a process are affected by additive circulatory noise in a closedloop. The noise-free input–output data of the process are obtained using the proposed method by removing these circulatory noise components. The process model can be achieved by using instrumental variable estimation method with prefiltered noise-free input–output data. The performance of the proposed hybrid parameter estimation scheme is evaluated by the Monte Carlo simulation analysis. Simulation results illustrate the efficacy of the proposed procedure. The methodology has been successfully applied in tuning of IMC based flow controller and a practical application demonstrates the applicability of the algorithm.

DPCM-based vibration sensor data compression and its effect on structural system identification

Due to the large scale and complexity of civil infrastructures, structural health monitoring typically requires a substantial number of sensors, which consequently generate huge volumes of sensor data. Innovative sensor data compression techniques are highly desired to facilitate efficient data storage and remote retrieval of sensor data. This paper presents a vibration sensor data compression algorithm based on the Differential Pulse Code Modulation (DPCM) method and the consideration of effects of signal distortion due to lossy data compression on structural system identification. The DPCM system concerned consists of two primary components: linear predictor and quantizer. For the DPCM system considered in this study, the Least Square method is used to derive the linear predictor coefficients and Jayant quantizer is used for scalar quantization. A 5-DOF model structure is used as the prototype structure in numerical study. Numerical simulation was carried out to study the performance of the proposed DPCM-based data compression algorithm as well as its effect on the accuracy of structural identification including modal parameters and second order structural parameters such as stiffness and damping coefficients. It is found that the DPCM-based sensor data compression method is capable of reducing the raw sensor data size to a significant extent while having a minor effect on the modal parameters as well as second order structural parameters identified from reconstructed sensor data.

基于Mask R-CNN的油田井场指针仪表识别方法研究

针对无人机巡检流程中采集到井场仪表图像模糊以及油田仪表定位模型实时性较差的问题,提出一种改进后最大后验概率模型去模糊方法和基于Mask R-CNN的指针式仪表定位算法。首先,通过采用变步长LMS滤波器的方法优化图像的先验信息,根据输入数据的统计特性调整滤波器参数,生成初步的仪表图像恢复结果,从而提升了最大后验概率的去模糊效果;其次,在Mask R-CNN网络结构的基础上,选用MobileNetV3作为主干特征提取网络减少参数量,再加入注意力机制模块保证准确率以完成仪表定位。最后,实验证明,仪表图像评价指标高于其他算法,该文提出的仪表定位算法减少了48.25 M参数量,FPS值达到37.3 frame/s,准确率为94.02%。

基于UDI技术的单件器械追溯系统建设与应用探讨

为提高单件器械在回收、清洗、核包、灭菌及使用等环节的追溯精准度,提高贵重器械的利用率和成本管控水平,医院在消毒供应中心物品追溯系统信息化平台上,开发了“基于UDI技术的消毒供应中心单件器械追溯系统”。通过在单件器械上刻印UDI,在回收、器械组配两个环节扫描UDI码,记录单件器械的使用次数、单包清洗灭菌次数和单包使用明细,有效减少不必要的浪费,降低清洗消毒成本和器械采购开支,为手术质量管理提供支持。

货币政策冲击与企业投资:数字金融的调节效应

近年来,中国金融领域的一个显著标志是数字金融的蓬勃发展,这一新兴趋势会对货币政策的目标和实施效果产生影响。使用工具变量、高频识别法和SVAR模型识别货币政策冲击序列,分析数字金融发展如何调节货币政策冲击对企业投资的影响。研究发现,数字金融发展强化了货币政策冲击对企业投资的影响。异质性分析表明,该强化作用对非国有企业、规模较小企业、高科技行业和宽松性货币政策较为明显。进一步分析发现,数字金融强化货币政策冲击对企业投资的影响主要是通过降低企业融资约束、提升企业价值和提高企业风险承担水平三种机制实现。

基于轻量化神经网络和SimAM注意力机制的电力仪表检测与识别

通过图像识别算法对电力仪表进行识别与读数可有效避免人工巡检过程中的诸多不确定问题。针对传统仪表检测识别方法工作量大以及指针分割不清晰导致读数不准确的问题,提出了一种基于轻量化神经网络模型和SimAM注意力机制的电力仪表检测与识别方法。首先,通过引入SimAM注意力机制以及YOLOv5s轻量化神经网络模型实现对电力仪表的识别与分类以及表盘区域的分割;然后分别采用CRNN文本识别算法和Hough圆检测方法对数字式仪表以及指针式仪表进行读数。模型结合多种场景进行训练,并对识别与读数2个阶段分别给出评价标准。实验结果表明,该方法能够高效完成电力仪表的检测与识别工作,在提高检测准确率的同时将总体检测时间控制在1.00 s以内,具有一定的实用性。

基于高分辨质谱的中药学本科实验课程教学探索

中药制剂是由多种中药配伍组成的,是一个复杂的分子体系,其分析鉴定工作存在较大难度。高效液相色谱与高分辨质谱联用系统(HPLC-HRMS)在中药复方的定性研究中发挥着重要作用。本论文通过探索将高分辨液相色谱质谱联用系统应用到中药学本科生实验教学实践中,建立了对中药制剂参松养心胶囊中5种特征性成分进行鉴定的实验教学方法。使学生了解高分辨质谱在中药制剂分析和鉴定中的重要应用,开阔了本校中药学专业本科生的科研视野,提高了学生对仪器分析的理解,对培养高素质高水平的药学本科生起到了积极作用。

面向配电柜字符识别的YOLOv7-MSBP目标定位算法

通过机器视觉算法精确定位配电柜仪表的位置是实现仪表智能化识别的关键。针对配电柜背景复杂、字符尺度多样和相机像素低而导致的目标定位精度不高问题,提出一种面向配电柜字符识别的YOLOv7-MSBP目标定位算法。首先,设计Micro-branch检测分支,改进初始锚框铺设间隔,从而提高对小目标的检测精度。其次,引入双向特征金字塔网络(BiFPN)跨尺度融合不同层特征值,以改善因下采样造成的细节特征丢失、特征融合不充分的现象;同时,设计同步混合阈卷积注意力模块(Syn-CBAM),加权融合通道和空间注意力特征,以提升算法的特征提取能力;并且,在主干网络引入部分卷积(PConv)模块,以降低算法冗余和延迟,提高检测速度。最后,将YOLOv7-MSBP的定位结果送入Paddle OCR(Optical Character Recognition)模型识别字符。实验结果表明,YOLOv7-MSBP算法的平均精度均值(mAP)达到93.2%,与YOLOv7算法相比提高了4.3个百分点,可见所提算法能够快速准确定位识别配电柜字符,验证了所提算法的有效性。

基于STM32与LabVIEW的CAN总线创新实训平台设计

基于STM32处理器设计了用于课程实训的虚拟仪器LabVIEW数据采集板硬件电路,同时在嵌入式Keil编译器环境下实现了各个模块的接口功能。上位PC机通过LabVIEW软件使用事先定义的CAN应用层协议对采集板模拟I/O、数字I/O以及RFID、MPU6000传感器的信息进行采集处理。该实训平台目前已经在某公司六关节协作型机器人末端接口系统测试应用,结果表明采集板实训平台稳定性、精度都能满足接口设计要求。

基于改进YOLOv5的外科手术器械识别系统的开发

目的:基于改进型You Only Look Once V5(YOLOv5)人工智能开发手术器械识别系统。方法:收集常用外科手术器械10类,包括治疗碗、药杯、弯盘、针持器、血管钳、刀柄、组织拉钩、手术刀片、缝针、棉球。将收集的器械置于同一视野下,随机改变不同器械放置位置和状态,在不同拍照方位、布料背景、光线角度和强弱环境下拍摄照片806张。将拍摄的照片按照7∶3随机划分为人工智能训练组和验证组。采用精确度、召回率、平均精度、平均精度均值和F1得分值等参数比较原始YOLOv5模型和改进模型S-YOLOv5的算法识别性能。结果:与原始YOLOv5模型相比,改进模型S-YOLOv5表现出更高的识别性能,其精确率、召回率、平均精度和F1得分值分别为0.978,0.973,0.926,0.975。改进模型S-YOLOv5对各手术器械的识别准确率均高于原始YOLOv5模型。结论:基于S-YOLOv5的人工智能辅助手术器械识别系统具有较好的分类能力和定位能力,为人工智能辅助手术器械清点提供了初步探索和思路。

Identification of the flavor profiles of Chinese pancakes from various areas using smart instruments combined with E-noses and E-tongues

In order to reveal the flavor characteristics of Chinese pancakes,the aroma and taste compounds of seven traditional Chinese pancakes were identified.The results showed that electronic nose(E-nose)analysis with PCA could successfully distinguish the aroma profiles of seven Chinese pancakes;the principal components PC1 and PC2 represented 75.74%and 23.2%of the total variance(98.94%)respectively.Meanwhile,the discrimination index of taste profiles of seven Chinese pancakes based on electronic tongue(E-tongue)analysis with LDA was 99.32%;the discriminant factors DF1 and DF2 represented 94.99%and 4.33%of the total variance respectively.Furthermore,GC-MS results demonstrated that thirty-threeflavor compounds were identified in seven Chinese pancakes,including aldehydes,alcohols,alkanes,acids,and aromatics.Among the flavor components,aldehydes with ROAVs higher than 1 contributed most significantly to the overall aroma,such as(E,E)-2,4-nonadienal present the largest contribution in Qingzhou pancake,Jinan and Yishui pancake;hexanal present the largest contribution in Shenxian and Gaomi pancake;nonanal and benzeneacetaldehyde present the largest contribution in Linqu and Tai’an pancake,respectively.The umami and sweet taste amino acids were the most abundant in all the Chinese pancake samples,and Qingzhou pancake had relatively high amino acid content.The content of glucose was higher than maltose in Gaomi,Shenxian,and Tai’an pancakes,whereas the content of maltose was higher than glucose in Linqu,Qingzhou,Jinan,and Yishui pancakes.These results indicated that the aroma and taste profiles of Chinese pancakes differed significantly in terms of their flavor compound composition.The presented results could be beneficial for providing a comprehensive method for flavor profile identification of traditional whole-grain-based staples such as Chinese pancakes.

基于环形电导传感器的气液两相流流型识别与过程参数测量

针对水平管道气液两相流,提出一种仅采用单模态电导传感器实现流型准确辨识和流速、含率准确测量的综合性测试方法。首先,采用由6个电极环组成的电导传感器在线获取不同流动状态下含率和速度的相关信息。其次,在信号波动分析基础上,揭示了不同流型下的流动特性,进而提取了量纲为1电压序列的均值和方差及互相关速度作为流型表征的特征向量;采用适用于小样本的支持向量机方法,以“一对一”策略构建了15个以径向基为核函数的二分类器用于分层流、波状流、泡状流、塞状流、弹状流和环状流的划分,采用交叉验证方法对模型参数进行了优化选取,实现了6种流型的准确识别,平均识别率为93.1%。最后,在流型划分基础上,针对性地提出利用量纲为1电压和互相关速度获取不同流型下分相含率和平均速度的计算模型,并与入口参考含率和参考流速进行了对比。动态实验表明,含水率和含气率的均方根误差分别为2.56%和2.73%,平均流速的均方根误差为0.69m/s。

X线透视下血管腔内介入手术器具自动识别与跟踪研究进展

血管腔内介入手术器具自动识别与跟踪有利于血管疾病精准智能微创诊治及手术机器人自动化。随着人工智能(AI)不断发展,识别与跟踪技术的准确率和实时性也在不断提高,更加适应临床需求。本文综述了X线透视下血管腔内介入手术器具自动识别与跟踪研究进展。首先,总结和阐述了介入手术器具自动识别与跟踪相关技术;其次,从完全监督和弱监督两个角度总结了介入手术器具识别与跟踪算法;最后,对介入手术器具识别与跟踪技术应用场景进行了较为全面的总结,包括手术辅助决策、手术智能导航和手术增强现实(AR)技术培训。

基于巡检机器人的数字仪表自动识别方法

随着信息化技术的蓬勃发展和,改革了传统的巡检方式。基于巡检机器人,具有信赖性高和适合各种仪表盘的特性,加强了数字仪表的自我识别能力。通过、数码仪表盘和开关等要素的影像,经过智能分析后进行异常警报。巡检机器人代替了人工的工作,具有广阔的应用前景。在数字教程的数字识别阶段,使用多尺度探测算法,提供了数字元数据的模拟方法。巡检机器人对数据拍摄效果明显,有效地提高了的数字仪表自动识别速度和准确度。

行动者认知、制度结构与政策工具选择——基于广东省J市低收入人口识别机制设计过程的分析

政策工具选择是行动者认知、政策情景、制度结构等多因素共同作用的结果,行动者认知与制度结构的动态性可能引起政策工具选择的变化。选取广东省J市低收入人口识别机制设计过程作为研究案例,以过程追踪为分析手段,提炼行动者认知与制度结构影响政策工具选择的作用机制。研究发现,科学知识与实践知识的互动促进了政策工具创新,但由于政治考量和制度的制约,政策工具选择出现了路径依赖。政策工具选择变动是政策学习与认知锁定两个机制先后作用的结果。

浅谈化妆品中铜绿假单胞菌和金黄色葡萄球菌检验能力验证方法与结果

为了提高化妆品中铜绿假单胞菌和金黄色葡萄球菌的检验能力,增强实验室间竞争能力,本实验室连续两年参加中检院NIFDC-PT中铜绿假单胞菌和金黄色葡萄球菌检验能力验证。按照作业指导书及《化妆品安全技术规范》(2015年版)的要求进行前期增菌及生化实验,采用Microfiex LT/SH Smart微生物质谱鉴定仪及VITEK 2 COMPACT全自动微生物鉴定仪对分离出的可疑菌进行鉴定。结果显示,两次能力验证结果均检出目标菌,与中检院指定值一致,结果满意。本文对实验过程及结果进行分析讨论,探讨提高检验结果准确性的方法。

基于改进YOLOv5轻量化的指针式仪表识别与读数方法研究

文章针对指针式仪表自动读数存在的读数精度低、鲁棒性差及实时性不足等问题,提出了一种基于改进YOLOv5轻量化模型的指针式仪表识别与读数的方法。首先,采用改进的YOLOv5识别并定位复杂场景中待检测仪表的位置,提取仪表区域;然后,通过特征点匹配与透视变换对仪表图像进行校正;最后,利用M-LSD算法提取指针并通过直线拟合计算出指针所指向的刻度读数。试验结果表明:文章提出的方法最大误差为0.05mA,在最小刻度范围内,该方法具备良好的鲁棒性、精确性和实时性,可满足不同复杂场景下的实际应用。

基于改进的Faster RCNN的仪表自动识别方法

在环境复杂的工业场景中,仪表盘存在类别多、相似性高等问题,导致检测的识别效果较差、准确率不高。针对这一问题,提出了一种基于改进的更快速的区域卷积神经网络(Faster RCNN)的仪表自动识别方法。首先,采用残差网络(Resnet)101代替视觉几何群网络(VGG)16,进行了网络结构简化;然后,引入了特征金字塔网络(FPN),并将其改进为递归特征金字塔网络后进行了迭代融合,输出了特征图;接着,引入了注意力机制模块,根据特征的重要程度,完成了对输出通道权值的重新分配,增强了Faster RCNN对目标的运算能力;提出了改进非极大值抑制算法(Softer-NMS),通过降低置信度来确定准确的目标候选框;最后,采用Mosaic数据增强技术对可视对象类(VOC)2007数据集进行了扩充,对改进后的Faster RCNN模型进行了仪表自动识别的实验。研究结果表明:在相同工业环境下,与传统的Faster RCNN算法模型相比,改进后的Faster RCNN模型准确率为93.5%,较原模型提高了3.8%,mAP值为92.6%,较原模型提高了3.7%,可见该方法在实际生产中具有较强的鲁棒性与泛化能力,可满足工业上对智能检测的要求。