Fuzzy-Model-Based Finite Frequency Fault Detection Filtering Design for Two-Dimensional Nonlinear Systems

This article studies the fault detection filtering design problem for Roesser type two-dimensional(2-D)nonlinear systems described by uncertain 2-D Takagi-Sugeno(T-S)fuzzy models.Firstly,fuzzy Lyapunov functions are constructed and the 2-D Fourier transform is exploited,based on which a finite frequency fault detection filtering design method is proposed such that a residual signal is generated with robustness to external disturbances and sensitivity to faults.It has been shown that the utilization of available frequency spectrum information of faults and disturbances makes the proposed filtering design method more general and less conservative compared with a conventional nonfrequency based filtering design approach.Then,with the proposed evaluation function and its threshold,a novel mixed finite frequency H_(∞)/H_(-)fault detection algorithm is developed,based on which the fault can be immediately detected once the evaluation function exceeds the threshold.Finally,it is verified with simulation studies that the proposed method is effective and less conservative than conventional non-frequency and/or common Lyapunov function based filtering design methods.

Attention-based long short-term memory fully convolutional network for chemical process fault diagnosis

A correct and timely fault diagnosis is important for improving the safety and reliability of chemical processes. With the advancement of big data technology, data-driven fault diagnosis methods are being extensively used and still have considerable potential. In recent years, methods based on deep neural networks have made significant breakthroughs, and fault diagnosis methods for industrial processes based on deep learning have attracted considerable research attention. Therefore, we propose a fusion deeplearning algorithm based on a fully convolutional neural network(FCN) to extract features and build models to correctly diagnose all types of faults. We use long short-term memory(LSTM) units to expand our proposed FCN so that our proposed deep learning model can better extract the time-domain features of chemical process data. We also introduce the attention mechanism into the model, aimed at highlighting the importance of features, which is significant for the fault diagnosis of chemical processes with many features. When applied to the benchmark Tennessee Eastman process, our proposed model exhibits impressive performance, demonstrating the effectiveness of the attention-based LSTM FCN in chemical process fault diagnosis.

Temperature-Triggered Hardware Trojan Based Algebraic Fault Analysis of SKINNY-64-64 Lightweight Block Cipher

SKINNY-64-64 is a lightweight block cipher with a 64-bit block length and key length,and it is mainly used on the Internet of Things(IoT).Currently,faults can be injected into cryptographic devices by attackers in a variety of ways,but it is still difficult to achieve a precisely located fault attacks at a low cost,whereas a Hardware Trojan(HT)can realize this.Temperature,as a physical quantity incidental to the operation of a cryptographic device,is easily overlooked.In this paper,a temperature-triggered HT(THT)is designed,which,when activated,causes a specific bit of the intermediate state of the SKINNY-64-64 to be flipped.Further,in this paper,a THT-based algebraic fault analysis(THT-AFA)method is proposed.To demonstrate the effectiveness of the method,experiments on algebraic fault analysis(AFA)and THT-AFA have been carried out on SKINNY-64-64.In the THT-AFA for SKINNY-64-64,it is only required to activate the THT 3 times to obtain the master key with a 100%success rate,and the average time for the attack is 64.57 s.However,when performing AFA on this cipher,we provide a relation-ship between the number of different faults and the residual entropy of the key.In comparison,our proposed THT-AFA method has better performance in terms of attack efficiency.To the best of our knowledge,this is the first HT attack on SKINNY-64-64.

Causal temporal graph attention network for fault diagnosis of chemical processes

Fault detection and diagnosis(FDD)plays a significant role in ensuring the safety and stability of chemical processes.With the development of artificial intelligence(AI)and big data technologies,data-driven approaches with excellent performance are widely used for FDD in chemical processes.However,improved predictive accuracy has often been achieved through increased model complexity,which turns models into black-box methods and causes uncertainty regarding their decisions.In this study,a causal temporal graph attention network(CTGAN)is proposed for fault diagnosis of chemical processes.A chemical causal graph is built by causal inference to represent the propagation path of faults.The attention mechanism and chemical causal graph were combined to help us notice the key variables relating to fault fluctuations.Experiments in the Tennessee Eastman(TE)process and the green ammonia(GA)process showed that CTGAN achieved high performance and good explainability.

矿井通风系统智能故障诊断MC-OCSVM模型

为解决矿井通风系统故障分支判识不准确的问题,引入单分类算法,构建了多个单分类支持向量机(One-Class Support Vector Machines, OCSVM)集成的通风系统故障诊断模型。模型采用统一超参数并设计了尺度统一公式以实现多个输出尺度的统一,将通风系统故障诊断问题转变为最大决策距离问题,建立仅需正常样本参与训练的通风系统故障诊断半监督学习模型,实现对矿井监测风速数据的有效利用。进行了KEEL公开数据集和东山煤矿生产矿井实例试验,结果表明,单分类集成模型能够解决多分类问题,与其他单分类集成模型相比,单分类支持向量机集成(Multi-Class One-Class SVM,MC-OCSVM)模型具有最佳的泛化性,所提模型能够快速准确地识别通风系统故障分支,故障诊断准确率达93.2%,单次故障诊断时间为1.2 s,具有较强的鲁棒性。研究工作是实现矿井通风智能化的基础,为通风系统故障诊断提供技术支撑。

融合BWOSP-VMD-TOPSIS降噪和深度学习的旋转机械故障诊断

提出了一种融合改进白鲸优化算法(Beluga Whale Optimization with Stranding Phase,BWOSP)、变分模态分解(Variational Mode Decomposition,VMD)和理想排序法(Technique for Order of Preference by Similarity to Ideal Solution,TOPSIS)构建综合指标,并结合深度学习的旋转机械故障诊断方法。首先,通过加入“搁浅”阶段建立了一种新型BWOSP算法;其次,利用BWOSP-VMD得到(K,α)最优参数组合;再次,考虑各本征模态分量的中心频率、相关性系数、峭度指标和包络熵通过TOPSIS构建综合指标并进行筛选、重构;最后,将BWOSP-VMD-TOPSIS降噪方法与多种深度学习模型相结合,以某轴承故障为例计算了故障诊断准确率和F1值,并与多种方法对比验证了方法的有效性和泛化性。结果表明,基于BWOSP-VMD-TOPSIS和深度学习的故障诊断方法能对含有强噪声干扰的旋转机械故障信号有效降噪并准确进行故障诊断,具有较强的泛化能力。

基于CNN-LSTM故障预测模型的客滚船安全评估研究

为提高客滚船安全评估准确性,针对电力系统监测数据的多维和时序特性,提出基于CNN-LSTM混合神经网络的客滚船电力系统故障预测模型。首先利用卷积神经网络(CNN)对涵盖多维参数的电力系统时间序列数据进行特征提取,降低特征维度,提高特征表示能力,然后将提取的特征序列输入到长短期记忆(LSTM)网络中进行时序建模和故障预测。结果表明,对比ARIMA、LR、LSTM、CNN等故障预测模型,CNN-LSTM混合神经网络模型整体预测精度分别提高了12.8%、5.07%、4.19%、4.33%,故障预测效果良好。

基于POA-RVM模型的抽蓄机组故障诊断

有效的故障诊断方法不仅能快速、准确地辨别抽蓄机组故障类型,还能降低抽水蓄能电站的运行维护成本。针对相关向量机(RVM)有关参数的调整不当导致诊断结果受影响的问题,提出利用鹈鹕优化算法(POA)对相关向量机参数的选取进行优化,构建鹈鹕优化算法和相关向量机组合的分类模型(POA-RVM)。选取仙居抽水蓄能电站4台抽蓄机组在5种状态下的数据进行预处理和特征选取后构成故障样本集,并分别采用标准相关向量机,以及用遗传算法、粒子群算法和灰狼算法优化的相关向量机模型对这些故障样本进行分类。结果表明:与标准相关向量机,以及经遗传算法、粒子群算法和灰狼算法优化的相关向量机模型相比,POA-RVM模型有效提高了抽蓄机组故障诊断的准确率。

基于SSA-BP的通信设备故障检测

BP神经网络是故障检测的常用方法,但是在装备故障诊断的运用中,其很难快速有效地获得正确数量的网络层和神经元,而且学习速度较慢,导致检测效率低、稳定性差。为提高某型通信设备的故障诊断效能,论文在以BP神经网络作为诊断算法的基础上,引入麻雀搜索算法(SSA)这种新型优化算法改进BP神经网络参数的选取,优化参数设置,提高检测速度。相关改进算法运用于某型通信设备故障检测,与传统的BP神经网络算法相对比,采用麻雀搜索优化的BP神经网络故障检测算法在诊断效能方面优势明显,为开展装备维护,提供了很好的指导作用,也为后续相关诊断软件平台的开展提供了算法基础。

FTA-BN在机场跑道入侵事故影响因素分析中的应用

为了分析机场跑道侵入的影响因素,更有针对性地对预防机场跑道侵入提出合理建议,结合相关信息通告中统计的数据,首先从人员因素、环境因素、设备因素和管理因素4个方面分析跑道侵入的事故成因,并建立了故障树(Fault Tree Analysis,FTA)模型和贝叶斯网络(Bayesian Network,BN)模型,然后利用软件Netica对贝叶斯网络模型进行了后验概率推理与敏感性分析,最后根据分析结果提出了相应的建议。结果表明,人员因素影响程度最大,其次是管理因素,而环境因素和设备因素的影响程度相对偏小。

基于KPCA-SVM的S700K转辙机故障诊断方法

针对S700K转辙机动作功率曲线非线性特征多样化、复杂化的特点,提出了一种基于核主成分分析(Kernel Principal Component Analysis,KPCA)和支持向量机(Support Vector Machine,SVM)的智能故障诊断方法。首先,对S700K转辙机的功率曲线进行分析,研究正常曲线变化规律,总结常见故障类型功率曲线的变化现象和故障原因。然后,从功率曲线中提取10种时域特征值组成初始特征数据集,用KPCA算法将特征数据映射到高维特征空间中对其进行PCA降维,得到故障样本的非线性主成分。最后,将得到的非线性主成分作为多分类SVM的输入样本进行故障模式识别。采用粒子群优化(Particle Swarm Optimization,PSO)算法分别对核函数参数和SVM惩罚因子进行优化,提高模型的诊断精度。仿真结果表明,该模型能够有效提取转辙机故障信号的非线性特征,故障诊断精度达到97%,诊断时间较短,适用于准确性、实时性要求更高的提速道岔。

基于Vague集-可拓模型的断层富水区桥梁运营安全评估

为了探究断层富水区复杂地质环境对桥梁运营安全状况的影响并科学合理做出评估,从富水性特征、地质构造、桥梁结构参数、运营监测和安全管理5方面出发构建断层富水区桥梁多层次评估指标体系,将含有语言变量的Vague集设计主观权重与简洁高效的EW法设计客观权重相结合,并通过距离函数优化分配系数优化组合赋权,基于物元可拓理论建立断层富水区桥梁运营安全状态综合评估模型并应用于甘肃省某座桥梁实例中,引入安全性级别变量特征值确定评估桥梁的安全等级。研究结果表明:待评桥梁安全等级为Ⅱ级,运营状态比较安全,评估结果与现场情况基本相符,验证其评估模型的客观性与适用性。研究结果可为此类区域桥梁的加固养护提供决策依据。

Early faults prediction of running state of electromechanical systems and reconfigurable integration of series safety monitoring systems

Fault prediction technology of running state of electromechanical systems is one of the key technologies that ensure safe and reliable operation of electromechanical equipment in health state. For multiple types of modern, high-end and key electromechanical equipment, this paper will describe the early faults prediction method for multi-type electromechanical systems, which is favorable for predicting early faults of complex electromechanical systems in non-stationary, nonlinear, variable working conditions and long-time running state; the paper shall introduce the reconfigurable integration technology of series safety monitoring systems based on which the integrated development platform of series safety monitoring systems is built. This platform can adapt to integrated R&D of series safety monitoring systems characterized by high technology, multiple species and low volume. With the help of this platform, series safety monitoring systems were developed, and the Remote Network Security Monitoring Center for Facility Groups was built. Experimental research and engineering applications show that: this new fault prediction method has realized the development trend features extraction of typical electromechanical systems, multi-information fusion, intelligent information decision-making and so on, improving the processing accuracy, relevance and applicability of information; new reconfigurable integration technologies have improved the integration level and R&D efficiency of series safety monitoring systems as well as expanded the scope of application; the series safety monitoring systems developed based on reconfigurable integration platform has already played an important role in many aspects including ensuring safety operation of equipment, stabilizing product quality, optimizing running state, saving energy consumption, reducing environmental pollution, improving working conditions, carrying out scientific maintenance, advancing equipment utilization, saving maintenance charge and enhancing the level of information management.

Fault plane parameters of Sanhe-Pinggu M8 earthquake in 1679 determined using present-day small earthquakes

The great Sanhe-Pinggu M8 earthquake occurred in 1679 was the largest surface rupture event recorded in history in the northern part of North China plain. This study determines the fault geometry of this earthquake by inverting seismological data of present-day moderate-small earthquakes in the focal area. We relocated those earthquakes with the double-difference method. Based on the assumption that clustered small earthquakes often occur in the vicinity of fault plane of large earthquake, and referring to the morphology of the long axis of the isoseismal line obtained by the predecessors, we selected a strip-shaped zone from the relocated earthquake catalog in the period from 1980 to 2009 to invert fault plane parameters of this earthquake. The inversion results are as follows： the strike is 38.23°, the dip angle is 82.54°, the slip angle is -156.08°, the fault length is about 80 km, the lower-boundary depth is about 23 km and the buried depth of upper boundary is about 3 kin. This shows that the seismogenic fault is a NNE-trending normal dip-slip fault, southeast wall downward and northwest wall uplift, with the right-lateral strike-slip component. Moreover, the surface rupture zone, intensity distribution of the earth-quake and seismic-wave velocity profile in the focal area all verified our study result.

Internal structures and high-velocity frictional properties of Longmenshan fault zone at Shenxigou activated during the 2008 Wenchuan earthquake

This paper reports internal structures of a wide fault zone at Shenxigou,Dujiangyan,Sichuan province,China,and high-velocity frictional properties of the fault gouge collected near the coseismic slip zone during the 2008 Wenchuan earthquake.Vertical offset and horizontal displacement at the trench site were 2.8 m（NW side up）and 4.8 m（right-lateral）,respectively.The fault zone formed in Triassic sandstone,siltstone,and shale about 500 m away from the Yingxiu-Beichuan fault,a major fault in the Longmenshan fault system.A trench survey across the coseismic fault,and observations of outcrops and drill cores down to a depth of 57 m revealed that the fault zone consists of fault gouge and fault breccia of about0.5 and 250-300 m in widths,respectively,and that the fault strikes N62°E and dips 68° to NW.Quaternary conglomerates were recovered beneath the fault in the drilling,so that the fault moved at least 55 m along the coseismic slip zone,experiencing about 18 events of similar sizes.The fault core is composed of grayish gouge（GG） and blackish gouge（BG） with very complex slip-zone structures.BG contains low-crystalline graphite of about 30 %.High-velocity friction experiments were conducted at normal stresses of 0.6-2.1 MPa and slip rates of 0.1-2.1 m/s.Both GG and BG exhibit dramatic slip weakening at constant high slip rates that can be described as an exponential decay from peak friction coefficient lpto steadystate friction coefficient lssover a slip-weakening distance Dc.Deformation of GG and BG is characterized by overlapped slip-zone structures and development of sharp slickenside surfaces,respectively.Comparison of our data with those reported for other outcrops indicates that the high-velocity frictional properties of the Longmenshan fault zones are quite uniform and the high-velocity weakening must have promoted dynamic rupture propagation during the Wenchuan earthquake.

Fault-tolerant Control Systems-An Introductory Overview

This paper presents an introductory overview on the development of fault-tolerant control systems. For this reason, the paper is written in a tutorial fashion to summarize some of the important results in this subject area deliberately without going into details in any of them. However, key references are provided from which interested readers can obtain more detailed information on a particular subject. It is necessary to mention that, throughout this paper, no efforts were made to provide an exhaustive coverage on the subject matter. In fact, it is far from it. The paper merely represents the view and experience of its author. It can very well be that some important issues or topics were left out unintentionally. If that is the case, the author sincerely apologizes in advance.After a brief account of fault-tolerant control systems, particularly on the original motivations, and the concept of redundancies, the paper reviews the development of fault-tolerant control systems with highlights to several important issues from a historical perspective. The general approaches to fault-tolerant control has been divided into passive, active, and hybrid approaches. The analysis techniques for active fault-tolerant control systems are also discussed. Practical applications of faulttolerant control are highlighted from a practical and industrial perspective. Finally, some critical issues in this area are discussed as open problems for future research/development in this emerging field.

基于RF特征优选和WOA-ELM的风电齿轮箱故障诊断

针对风电机组齿轮箱故障特征提取不足,故障诊断率低问题,提出了一种基于RF特征优选,结合WOA-ELM特征识别的风电齿轮箱故障诊断方法。首先,提取风电齿轮箱时域、频域、时频域特征,构建多域高维特征集;其次,利用RF进行特征重要度排序并提取10维优选特征;最后,利用WOA优化调整ELM模型的输入权值和隐含层阈值,实现风电齿轮箱故障分类识别。将本文方法应用于风电齿轮箱故障诊断,实验结果表明,本文方法平均诊断率能达到99.81%,诊断准确率均高于对比方法且诊断用时最少,能够有效地进行风电齿轮箱故障诊断。

基于FTA-BN的综合交通枢纽中地铁车站安全风险评价

以综合交通枢纽中的地铁车站安全为研究目标,综合考虑综合交通枢纽中特殊的客流组成和乘客特征,以踩踏、火灾、水灾、公共卫生和大面积滞留5类易发风险事故作为研究对象,基于FTA-BN方法对其影响因素进行分析,识别其风险因素,建立相应的事故树模型,转化为贝叶斯网络模型进行风险评价;引入三角模糊数处理专家自然语言,得到贝叶斯网络中的先验概率和条件概率分布,然后通过贝叶斯网络模型进行网络推理计算和敏感性分析,找出地铁车站中的薄弱部分,制定相应的风险管控措施,从而提高枢纽中地铁车站对于紧急事件的应对能力。以广州南站地铁车站为例进行快速评价,结果表明:广州南站在公共卫生安全方面存在一定危险,发生概率为42.98%,且较易发生大面积滞留事件,可能性为30.40%。

Intelligent monitoring-based safety system of massage robot

As an important attribute of robots, safety is involved in each link of the full life cycle of robots, including the design, manufacturing, operation and maintenance. The present study on robot safety is a systematic project. Traditionally, robot safety is defined as follows: robots should not collide with humans, or robots should not harm humans when they collide. Based on this definition of robot safety, researchers have proposed ex ante and ex post safety standards and safety strategies and used the risk index and risk level as the evaluation indexes for safety methods. A massage robot realizes its massage therapy function through applying a rhythmic force on the massage object. Therefore, the traditional definition of safety, safety strategies, and safety realization methods cannot satisfy the function and safety requirements of massage robots. Based on the descriptions of the environment of massage robots and the tasks of massage robots, the present study analyzes the safety requirements of massage robots; analyzes the potential safety dangers of massage robots using the fault tree tool; proposes an error monitoring-based intelligent safety system for massage robots through monitoring and evaluating potential safety danger states, as well as decision making based on potential safety danger states; and verifies the feasibility of the intelligent safety system through an experiment.

基于T-S模糊故障树和贝叶斯网络的建筑施工风险评估模型建立及应用

作为国民经济发展的支柱产业,建筑业安全事故频发,施工安全形势严峻。为有效评估和降低建筑施工安全风险,将T-S模糊故障树和贝叶斯网络进行结合,建立一种建筑施工风险评估模型。利用T-S门规则和贝叶斯网络的条件概率,建立T-S模糊故障树的贝叶斯网络转化模型,引入模糊理论对事件风险概率进行模糊化,最终借助贝叶斯网络双向推理算法计算故障概率、重要度及后验概率。结果表明,该模型能够根据基本事件风险概率进行量化计算,以正向推理方式计算体系事故发生概率;能够量化根节点的模糊重要度,确定事件重点管控顺序;且可以通过反向推理计算根节点后验概率,确定故障排查顺序。该计算模型最大限度贴近实际施工情形,更加科学合理地进行建筑施工风险评估,可为建筑施工的安全风险评估和精准化管理提供理论支持。