Automatic well test interpretation based on convolutional neural network for a radial composite reservoir

An automatic well test interpretation method for radial composite reservoirs based on convolutional neural network(CNN) is proposed, and its effectiveness and accuracy are verified by actual field data. In this paper, based on the data transformed by logarithm function and the loss function of mean square error(MSE), the optimal CNN is obtained by reducing the loss function to optimize the network with "dropout" method to avoid over fitting. The trained optimal network can be directly used to interpret the buildup or drawdown pressure data of the well in the radial composite reservoir, that is, the log-log plot of the given measured pressure variation and its derivative data are input into the network, the outputs are corresponding reservoir parameters(mobility ratio, storativity ratio, dimensionless composite radius, and dimensionless group characterizing well storage and skin effects), which realizes the automatic initial fitting of well test interpretation parameters. The method is verified with field measured data of Daqing Oilfield. The research shows that the method has high interpretation accuracy, and it is superior to the analytical method and the least square method.

Research of testing method based on UML statecharts

Unified modeling language （UML） is a powerful graphical modeling language with intuitional meaning. It provides various diagrams to depict system characteristics and complex environment from different viewpoints and different application layers. UML-based software development and modeling environments have been widely accepted in industry, including areas in which safety is an important issue such as spaceflight, defense, automobile, etc. To ensure and improve software quality becomes a main concern in the field. As one of the key techniques for software quality, software testing can effectively detect system faults. UML based software testing based is an important research direction in software engineering. The key to software testing is the generation of test cases. This dissertation studies an approach to generating test cases from UML statecharts.

On-line Detection of Gas Pipeline Based on the Real-Time Algorithm and Network Technology with Robot

The detection system integrates control technology, network technology, video encoding and decoding, video transmiss-ion, multi-single chip microcomputer communication, dat-abase technology, computer software and robot technology. The robot can adaptively adjust its status according to diameter (from 400 mm to 650 mm) of pipeline. The maximum detection distance is up to 1 000 m. The method of video coding in the system is based on fractal transformation. The experiments show that the coding scheme is fast and good PSNR. The precision of on-line detection is up to 3% thickness of pipeline wall. The robot can also have a high precision of location up to 0.03 m. The control method is based on network and characterized by on-line and real-time. The experiment in real gas pipeline shows that the performance of the detection system is good.

Development of a Model Driven ACSI Conformance Testing for IEC 61850-Based IED

Globally, traditional power systems are rapidly transforming towards the adoption of smart grid platforms. Substations which are at the center of the electric power transformation from the power plant are changing to IEC 61850 based digital substations. Therefore, within substation, there is a growing demand for the IEC 61850 based Intelligent Electronic Devices (IEDs). The operation of multiple manufacturers of IEDs in a single digital substation network increases the need for IEC 61850 communications specification conformance diagnosis to ensure interoperability for efficient data exchange between IEDs. The IEC 61850-10 presents test items for diagnosing communication specification conformance. There are many test tools available in the market today to test the compliance of the IEC 61850 communications specifications to the IED. In this paper, we propose a model-based diagnostic method for IED communication conformance testing. The proposed model-based software therefore uses the “drag and drop” technique to select the various IEC 61850 communication services (objects) required to design the test case in a user friendly Graphical User Interface (GUI). This makes the service conformance testing more flexible for test engineers and system integrators especially in situations that require test case modifications. Also, the proposed software tool makes it easy to understand the various IEC 61850 services using the friendly GUI.

Two-Tier GCT Based Approach for Attack Detection

The frequent attacks on network infrastructure, using various forms of denial of service attacks, have led to an increased need for developing new techniques for analyzing network traffic. If efficient analysis tools were available, it could become possible to detect the attacks and to take action to weaken those attacks appropriately before they have had time to propagate across the network. In this paper, we propose an SNMP MIB oriented approach for detecting attacks, which is based on two-tier GCT by analyzing causal relationship between attacking variable at the attacker and abnormal variable at the target. According to the abnormal behavior at the target, GCT is executed initially to determine preliminary attacking variable, which has whole causality with abnormal variable in network behavior. Depending on behavior feature extracted from abnormal behavior, we can recognize attacking variable by using GCT again, which has local causality with abnormal variable in local behavior. Proactive detecting rules can be constructed with the causality between attacking variable and abnormal variable, which can be used to give alarms in network management system. The results of experiment showed that the approach with two-tier GCT was proved to detect attacks early, with which attack propagation could be slowed through early detection.

Research on Key Technologies of Detecting 1553B Avionics Data Bus Network

1553B avionics data bus network may fail due to vibration,temperature,humidity or human error.Therefore,the research on detection technology of 1553B avionics data bus network is an important subject.The key technologies are studied by analyzing the possible faults of the network,including four-wire DC resistance measurement method for conductors-to-shield short test and stub continuity test,equivalent impedance measurement of coupling transformer for main bus continuity test,polarity reversal test base on duty ratio measurement,attenuation measurement base on coupler model,and data path integrity test base on bit error rate calculation.Finally,the implementation methods of key technologies are researched,a portable integrated automatic test system of 1553B data bus network is constructed based on PC 104 computer,and the hardware configuration and test process are especially designed.

Test Data Generation for Stateful Network Protocol Fuzzing Using a Rule-Based State Machine

To improve the efficiency and coverage of stateful network protocol fuzzing, this paper proposes a new method, using a rule-based state machine and a stateful rule tree to guide the generation of fuzz testing data. The method first builds a rule-based state machine model as a formal description of the states of a network protocol. This removes safety paths, to cut down the scale of the state space. Then it uses a stateful rule tree to describe the relationship between states and messages, and then remove useless items from it. According to the message sequence obtained by the analysis of paths using the stateful rule tree and the protocol specification, an abstract data model of test case generation is defined. The fuzz testing data is produced by various generation algorithms through filling data in the fields of the data model. Using the rule-based state machine and the stateful rule tree, the quantity of test data can be reduced. Experimental results indicate that our method can discover the same vulnerabilities as traditional approaches, using less test data, while optimizing test data generation and improving test efficiency.

数据驱动的脉冲风洞气动热试验数据分析方法探索

脉冲风洞的有效运行时间短,气动热测量信号易受干扰,通常采用人工判读的方式在大量的脉冲风洞测热试验数据中遴选有效数据,数据分析过程效率低、标准不统一。研究基于中国航天空气动力技术研究院1 m量级炮/激波双模式风洞气动热试验数据开展信号特征分析,确定了Fourier变换后的电压信号、总压-热流相关系数曲线、热流时间导数等参数对流动起止时间、运行模式分界时间、信号质量等关键信息的表征作用。在此基础上,基于卷积神经网络和密度基聚类算法,发展了传感器信号有效性判断模型、风洞有效运行时间段选取算法和传感器信号取值区间选取算法,实现了脉冲风洞气动热试验数据的智能处理。结果表明,智能算法对传感器信号有效性的判断准确度达到98%;针对3568条原始试验曲线进行处理,智能算法与人工方式得到的热流均值差异小于10%的数据约占91%,具有应用于风洞试验的价值。

一种针对船舶自动避碰算法召回测试的事故场景预测方法

在对船舶自动避碰算法进行仿真测试过程中发现缺陷并改进之后,需进行召回测试以验证改进的有效性,而随着被测算法的水平逐步提升,测试场景逐渐复杂,进行召回测试时难以设计更全面的测试场景。对此,提出一种能根据历史测试数据对新场景进行事故预测的卷积神经网络模型。通过该模型筛选出的场景与历史上发生过的事故场景属于同类,能支持更全面且有针对性的召回测试。在特征建模过程中,对测试场景进行9通道建模,以将场景信息表达为模型能识别的张量结构;在样本收集过程中,提出平行场景的方法,进行1次测试可收集到多组样本。在多样复杂场景中采用该预测方法对一种事故率为6.2%的被测避碰算法进行试验,结果发现该方法训练的模型从所有新的随机场景中筛选出24.9%的样本,这些筛出的场景以91.8%的概率覆盖所有事故场景。

5G非地面网络相关误差矢量幅度标准测试模型分析

针对泛在通信和万物智联的发展需求,地面5G蜂窝通信系统和非地面网络系统实现优势互补、融合发展、资源共享。非地面网络是一种全新的形态,文中先讨论5G非地面网络系统元素及相关应用场景,接着根据5G基站的测试方法和一致性要求,来分析误差矢量幅度测试的方法及相关指标,通过自主设计的程序生成的测试波形与商业软件生成的测试波形进行比对,从信噪比、信道带宽以及子载波间隔三个方面分析其对误差矢量幅度的影响。为非地面网络设备的设计研发提供基于3GPP最新标准的测试方法,可为相关设备大规模量产节省开销。

一种基于一维卷积神经网络的试井模型智能识别方法

为提高试井分析工作效率,实现试井模型的自动识别,提出了基于一维卷积神经网络(1D CNN)的试井模型智能识别方法。根据实测数据的特点,提出基于理论曲线构建样本库的原则与方法,并构建了4种常用油藏模型的训练样本库;建立了一维卷积神经网络模型,将样本库中双对数曲线的压力变化和压力导数数据作为输入,油藏类别作为网络输出训练及优化网络,总识别准确率可达99.16%,敏感度均在98%以上。经4口井实例应用,正确识别试井模型的概率大于0.99,与二维卷积神经网络相比,1D CNN显著降低了计算复杂度和时间成本,加快了训练速度。这表明基于试井理论所构建的样本库是有效的,能满足实测数据模型识别的需求;同时证明了方法的有效性、实用性和普适性。

基于对抗神经网络的力学试验机故障诊断系统设计

针对高校力学试验机随机故障频发问题,设计了力学试验机故障诊断系统。针对此类试验机使用间歇长、离散性强等特征,提出了基于离散性数据识别故障的设计思路。建立了机器学习知识库,基于对抗神经网络(GAN)理论设计了力学试验机故障诊断算法并建立了故障诊断系统,评价了故障诊断系统的性能指标。结果表明,所建立故障诊断系统在实验中的最低精确率、准确率和召回率分别达到96.12%、96.51%和95.15%,最高误识率仅为3.96%,性能满足使用要求。

电力工控网络私有通信协议安全性自动化测试方法

为了提高私有通信协议安全性自动化测试的效率和精度,提出电力工控网络私有通信协议安全性自动化测试方法。根据私有通信协议在传输过程中的能耗,计算私有通信协议传输过程中的误码率,利用误差补偿,完成电力工控网络私有通信协议的优化处理;确定遗传算法的编码与适应度函数,得到私有通信协议传输的最优路径,重构电力工控网络私有通信协议,得到电力工控网络私有通信协议安全性自动化测试步骤。实验结果表明,所提方法可以将测试延时和平均绝对误差分别控制在6 s以内和18%以内,提高私有通信协议安全性自动化测试的效率和精度。

深基坑自动化监测系统优化研究

通用版自动化监测系统难以满足基坑监测真实需求的现状,针对此问题,从监测基准网稳定性检校、改善通信链路、云平台数据展示等方面对通用版自动化监测系统进行优化改进,利用后验单位权方差Χ2检验方法对基准网稳定性进行检验,实时检校并更新监测基准网;采用基于LoRa通信的分布式监测站降低对基坑施工的干扰,并改善基坑内部信号传输环境;采用基坑方向位移、地下水位图示、开挖后累计变形等专业图表设计,提高云平台数据展示的专业性;并通过某建筑深基坑项目对优化内容进行应用验证,均取得了较好的应用效果,在保障监测数据准确性的同时,提高通用版自动化监测系统的行业针对性,为基坑自动化监测系统的建设发展提供了思路。

基于多传感器的化工有害气体自动预警系统研究

有害气体信号传输过程中受到通道干扰影响,会导致预警效果不佳。为了提高化工有害气体自动预警效果,设计了一种应用多传感器采集信息的化工有害气体自动预警系统。首先,选择多个传感器采集化工有害气体相关数据,构建数据采集适应性函数,以避免出现数据采集误差。然后,结合粒子群算法进行多传感器数据采集,构建高斯烟羽扩散模型。最后,计算化工有害连续源气体稳定浓度和气体泄漏速度,并依据计算结果作自动预警。试验结果表明,该系统监测的C_(2)H_(3)Cl、SO_(2)浓度值与实际数据分别存在最大仅为0.02×10^(-6)、0.01×10^(-6)的误差。该系统的预警效果较好,具有一定应用价值。

测试逻辑和测试数据分离模式的联锁测试脚本研究

针对测试逻辑和测试数据分离模式的联锁测试脚本进行研究,提出一种基于Python的测试逻辑和数据分离的脚本编写方法,在此基础上设计并实现与脚本适配的接口插件,提高联锁自动化测试系统的可用性和适应性。

网联车载终端软件自动化测试技术研究

网联车载终端Tbox作为智能网联的关键节点,车内与控制器通过传统CAN总线或车载以太网进行数据交互,车外与企业远程服务平台通过基站无线技术进行信息交互。实现Tbox应用软件自动放行测试,能够完成Tbox版本迭代升级的测试,有效提高软件开发品质和测试效率。

便携式列车工业以太网性能分析仪研制

文章中设计了一种便携式列车工业以太网性能分析仪,用于动车组和城轨车辆多场景下的工业以太网性能测试和智能分析。该分析仪具备人机交互界面、独立电池、丰富的接口、可扩展内存、高频数据采集器和专业测试软件。分析仪可实时监控分析以太网数据,并检查MAC、IP、带宽、TRDP报文、数据包等参数是否满足技术要求。同时,该分析仪还具有自动化预警功能和长时间记录网络数据的功能,可用于定位和解决列车运行中偶发且难以捕捉的网络故障。目前,该分析仪已应用于时速250 km中国标准动车组项目和深圳地铁20号线等项目中,实现了快速全面地对列车工业以太网网络进行测试和诊断。

基于遗传算法优化的SOFM神经网络生成测试数据集的方法

智能算法正成为软件测试领域新兴研究方向,运用智能算法生成复杂软件的测试数据已成为一种广受推崇的方法。采用基于遗传算法的技术生成测试数据,能够生成满足测试覆盖要求的少量测试数据。然而,对于生成大量测试数据集的情况来说,该方法并不适用。为了能够快速生成满足测试覆盖要求的数据集,提出一种基于遗传算法优化的自组织特征映射(SOFM)神经网络生成测试数据集的方法:首先,利用遗传算法的全局搜索能力,从海量数据中筛选出少量满足测试覆盖要求的代表性数据。接着,以这些遗传算法生成的测试数据为基础,结合SOFM神经网络强大的侧向联想能力,旨在生成大量满足测试覆盖要求的测试数据集。实验结果表明,该方法有效提高了测试数据集生成的效率。

基于5G双域专网的多场景自动拨测研究与应用

5G垂直行业2B网络智能运维是组成网络数智化转型的重要组成部分,为打通运维管理到市场支撑中间各个环节,提高5G双域专网的运维能力。对此,介绍了一种5G双域专网的多场景自动拨测模式,实现了5G ToC双域专网拨测异常检测能力,可以根据客户需求在5G toC双域专网业务质量监测、隐患挖掘、隐患预处理等多场景下使用,是支撑网络运维、前端市场的重要手段和工具。