基于半Markov决策过程的劣化系统检测与维修优化模型

针对系统劣化阶段持续时间、检测间隔时间和维修时间都服从一般分布的情况, 提出了一类基于半马氏决策过程的劣化系统检测与维修优化模型. 利用位相型分布近似一般分布简化了求解过程, 并提出了相应的改进值迭代算法. 最后通过算例验证了模型与迭代算法的可行性.     

Optimal inspection interval for a k-out-of-n system with non-identical components

In this paper, we develop a continuous-time discrete-state model for periodic inspection of a k-out-of-n cold-standby system with non-identical components. A perfect switching system detects the components’ failures, and the failed component(s) are repaired during the next inspection interval, and then added to the standby queue. The system can be in different states depending on the combination of working components and the order of the components on the standby queue at the beginning of an inspection interval. We present a matrix-based approach to determine the system states and calculate the system-states transition probabilities and the transition matrix. We calculate the expected total cost of the inspection intervals by determining the system state at the beginning and end of each inspection interval and calculating the inspection cost matrix. The expected total inspection cost consists of the system downtime cost, components repair cost, system repair cost, and system inspection costs. Finally, we minimize the system’s expected total cost by determining the system’s optimal inspection interval. The results show that determining the optimal inspection interval decreases the system's total inspection interval cost up to 60 % in comparison with the cases when the inspection interval is selected arbitrarily.     

A discounted integrated inspection-maintenance model for a single deteriorating production facility

In this paper, we address the problem of determining optimum inspection schedules for a single deteriorating production system with a predetermined replacement cycle. It is assumed that, at different discrete points in time over the fixed planning horizon, the facility is inspected to detect its operating state and then it goes over an imperfect preventive maintenance routine to enhance its operating performance. Moreover, the facility undergoes minimal repair once detected in an “out‐of‐control” state. We also adopt the concept of discounted cash flow analysis to account properly for the effect of time value of money on the inspection policies. Under these settings, we formulate the discounted integrated inspection‐maintenance problem as a dynamic programming model with general time to failure distribution. After illustrating the model with a numerical example, we perform sensitivity analysis to investigate the effects of some input parameters on the expected present worth and the number of inspections.     

Simultaneous determination of the optimal production–inventory and product inspection policies for a deteriorating production system

In this paper, we attempt to find a method for the optimization of production–inventory and product inspection policies for deteriorating production systems. Taking advantage of the nature of a deteriorating production system, a strategy would be not to inspect the first s items of the batch. Therefore, an inspection policy which disregards the first s (DTF-s) items of the batch is proposed. Under the DTF-s policy, we do not inspect the first s produced items but inspect only those items from the (s+1)th till the end of the production run. The objective of this study was the joint determination of the production lot size and the inspection policy s, resulting in a minimization of the expected average cost per unit time. Based on this model, the underlying conditions necessary for the existence of an optimal policy are given. Two commonly used inspection strategies, no inspection and full inspection are discussed. Under both inspection strategies, an optimal production–inventory lot is bounded by the traditional economic quantity. The case of full inspection is shown to be an extension of previously reported results. The option of investing in the process of quality improvement is also discussed. Finally, numerical examples are given to illustrate the method and its advantages in the conclusion.Scope and purposeThis paper considers the relationship between production, inventory and inspection in a deteriorating production system which may transit from the “in-control” state to the “out-of-control” state after a period of operation. Once the transition to the “out-of-control” state has occurred, it is assumed that some percentage of the items produced are defective or of substandard quality. However, in many cases, defects in a defective item can only be identified by an inspection process which carries an inspection cost. Those inspected items which are found to be defective are reworked at some cost before being shipped. On the other hand, defective items which are not inspected will be passed to the customer, incurring a much larger warranty cost. In order to operate such a system economically, tradeoffs among production setup, inventory, inspection and defective cost must be analyzed. Deterioration of the production system is an inherent process in all manufacturing industries. An understanding of the relationship among production, inventory and inspection for such systems will help managers to maintain efficient and economic control of operations.     

2类故障系统的检测策略研究

研究具有2类故障的可修系统的一个模型,假定系统工作时可能直接发生第1类故障, 也可能经过异常后发生第2类故障.系统故障时不需检测,系统工作时必须经过检测才能知道 它是正常还是异常,并且检测时间是一个随机变量.系统开始工作后,每隔一段时间对它检测 一次,直到系统故障或者检测结果是系统处于异常状态为止.利用密度演化方法,求出了系统的 可靠性指标和最优检测策略.     

State probability of a series-parallel repairable system with two-types of failure states

This paper presents a method for the analysis of a series-parallel safety-critical system where the system states can be distinguished into failure-safe and failure-dangerous. The method incorporates the Markov chain and universal generating function technique. In the model considered, both periodic inspection and repair (perfect and imperfect) of system elements are taken into account. The system state distributions and the overall system safety function are derived, based on the developed model. The proposed method is applicable to complex systems for analysing state distributions and it is also useful in decision-making such as determining the optimal proof-test interval or repair resource allocation. An illustrative example is given.     

基于状态转移系统的安全协议形式模型

提出一种基于状态转移系统的安全协议模型,以Dolev-Yao攻击者模型为前提假设,以状态转移系统为框架,用语义编码的方式定义消息和事件,用重写关系定义协议规则,用事件的集合来描述协议的安全属性,并给出安全属性的检验策略。该模型能够对安全协议进行精确的形式化描述,且便于实现自动化分析。     

Optimal number of minimal repairs before replacement of a deteriorating system with inspections

In this study, we propose a generalised replacement model for a deteriorating system with failures that could only be detected through inspection work. The system is assumed to have two types of failures and is replaced at the Nth type I failure (minor failure) or first type II failure (catastrophic failure), depending on whichever occurs first. The probability of type I and II failures depends on the number of failures since the last replacement. Such systems can be repaired upon type I failure, but are stochastically deteriorating, that is, the lengths of the operating intervals are stochastically decreasing, whereas the durations of the repairs are stochastically increasing. Then, the expected net cost rate is obtained. Some special cases are considered. Finally, a numerical example is provided.     

基于OpenFlow的SDN状态防火墙

提出了一种基于OpenFlow的状态检测防火墙系统,该方案通过在SDN控制器和交换机中添加状态表和变换流表,并根据包的类型分别制定相应的状态转换规则,实现对SDN网络状态的监测。最后,在开源控制器Floodlight和Open vSwitch上实现了一个基于状态检测的防火墙系统,并对该防火墙的性能进行了评估,结果表明基于OpenFlow的SDN状态检测防火墙能够识别不同类型的包并实现现有SDN防火墙不能实现的基于状态的细粒度访问控制。     

Replacement and standby redundancy policies in a deteriorating system with aging and random shocks

This study investigates the state-dependent maintenance policy in a multistate deteriorating production system with standby redundancy, assuming that the production system consists of one production unit and one single-server service center, and the key component of the production unit deteriorates over time. The key component deteriorates either from the current operating state to the next inferior operating state, due to aging, or from the current operating state to the failure state, due to a random shock. The deteriorating key component is replaced with a standby, according to a certain replacement policy, and sent to the service center for perfect repair; once completing the service, it joins the standbys for later production use. Both the sojourn time of a key component in each operating state, except the failure state, and the service time of a key component at the service center are assumed to be exponentially distributed. Taking into account the annual operating profit, measured in terms of production utilization and yield percentage of perfect items, and the annual operating costs, including the costs of key components and maintenance, this study jointly selects the operating state for replacing deteriorating key components and the level of standby redundancy in the system under the profit maximization objective. Numerical examples are given to illustrate the maintenance policies for systems with different transition probabilities in the deteriorating process, and the influence of transition probabilities on the maintenance policies are discussed.     

故障诊断和检测策略的综合研究

研究系统的故障诊断和检测策略问题．假定系统有两种工作状态(正常状态及异常状态)和一种故障状态，为判断系统是正常还是异常，每隔一段随机时间对系统检测一次．利用概率分析、补充变量和最优化方法，导出了系统一些新的运行指标、诊断参数的最优临界值和最优检测周期．     

时间Petri网的随机模拟

模拟是Peri网进行系统分析的常用方法之一。由于时间Petri网采用时间区间来描述变迁实施的时间范围,因此变迁的实施时间点在区间内是不确定的。提出了时间Petri网的随机模拟方法。该方法在变迁开始使能时,根据某种随机分布确定实施区间内的实施时间点;然后基于模拟仿真的实验数据,运用统计分析方法及算法,构造时间Petri网状态类树,计算变迁实施区间及实施概率,为时间Petri网的系统模拟提供了一种新的探索途径。     

基于无人机图像的黄河滩区违规牧羊智能检测方法

为解决传统的黄河滩区违规牧羊行为人工现场巡检方式效率低、监管难度大的问题,介绍一种针对黄河滩区违规牧羊的智能检测方法。提出一种改进的YOLOv5s目标检测算法,通过减小模型尺寸和计算量,提高算法的实时性能,同时设计一种羊群目标定位算法,通过建立相机中心、二维图像像点、空间地面目标物点三者之间的几何关系模型,判断牧羊行为是否发生在违规区域内。结果表明：改进后的YOLOv5s目标检测算法在CPU上的实时性能提升31.25%,训练自建黄河滩区牧羊数据集后模型大小仅为3.8 MB,目标定位算法的精度可控制在10 m以内,能够更快速精准地识别羊群。基于无人机图像的黄河滩区违规牧羊智能检测方法可实现无人化、智能化的黄河河道巡查,大大提高效率和灵活性,减少人力和物力投入,具有重要的现实意义和应用前景。     

Nondestructive evaluation sensor fusion with autonomous robotic system for civil infrastructure inspection

Civil infrastructure inspection is crucial to maintaining the quality of that infrastructure, which has a great impact on the economy. Performing this inspection is costly work that requires workers to be trained on how to use varying technologies, which can be error prone when performed manually and can result in damage to the infrastructure in some cases. For this reason, nondestructive evaluation (NDE) sensors are preferred for civil infrastructure inspection as they can perform the necessary inspection without damaging the infrastructure. In this paper, we develop a fully autonomous robotic system capable of real‐time data collection and quasi‐real‐time data processing. The robotic system is equipped with several NDE sensors that allow for a sensor fusion method to be developed that successfully minimizes inspection time while performing adequate inspection of areas that require more in‐depth data to be collected. A detailed discussion of the inspection framework developed for this robotic system, and the dual navigation modes for both indoor and outdoor autonomous navigation is presented. The developed robotic system is deployed to inspect several infrastructures (e.g., parking garages, bridges) at and near by the University of Nevada, Reno campus.     

一种输电线路巡检机器人控制系统的设计与实现

介绍了一种超高压输电线路巡检机器人控制系统的设计与实现方法．根据巡检作业任务的要求，采用遥控与局部自主相结合的控制模式实现巡检机器人沿线行走及跨越障碍．设计了巡检机器人有限状态机模型，实现了机器人遥控与局部自主控制的有机结合．采用基于激光传感器定位的方法实现了巡检机器人的自主越障控制．实验结果表明，该机器人可实现沿线行走及自主跨越障碍，从而验证了控制系统设计的有效性与合理性．     

基于混合马尔科夫树模型的ICS异常检测算法

针对工业控制系统中现有异常检测算法在语义攻击检测方面存在的不足,提出一种基于混合马尔科夫树模型的异常检测算法,充分利用工业控制系统的阶段性和周期性特征,构建系统正常运行时的行为模型|混合马尔科夫树.该模型包含合法的状态事件、合法的状态转移、正常的概率分布以及正常的转移时间间隔等4种信息,基于动态自适应的方法增强状态事件的关联度并引入时间间隔信息以实现对复杂语义攻击的检测,语义建模时设计一种剪枝策略以去除模型中的低频事件、低转移事件以及冗余节点,当被检测行为使得模型的以上4种信息产生的偏差超过阈值时,判定该行为异常.最后,基于OMNeT++网络仿真环境构建一个简化的污水处理系统对本文算法进行功能性验证,并利用真实物理测试床的数据集对算法的检测准确度进行性能验证.验证结果表明,本文算法能有效消除人机交互和常规诊断等操作带来的噪声影响,对复杂语义攻击具有较高的检出率,且能识别传统的非语义攻击.     

Optimal non-periodic inspection scheme for a multi-component repairable system using A search algorithm

This paper proposes an approach for finding an optimal non-periodic inspection scheme on a finite time horizon for a multi-component repairable system. The system consists of several components, each of which is subjected to soft failure. Soft failures of each component do not cause the system to stop functioning, but increase the system operating costs and are detected only if inspection is performed. Thus, the system is inspected at the scheduled inspection instances and if any of its components is found to have failed, the failed component is minimally repaired. The system’s expected total cost associated with a given inspection scheme includes inspection costs, repair costs, and the penalty costs that are incurred due to the time delay between the actual occurrence of a soft failure of the components and its detection at an inspection. The objective is to determine the optimal inspection scheme which minimizes system’s expected total cost.     

Real-time reliability prediction for dynamic systems with both deteriorating and unreliable components

As an important technology for predictive maintenance, failure prognosis has attracted more and more attentions in recent years. Real-time reliability prediction is one effective solution to failure prognosis. Considering a dynamic system that is composed of normal, deteriorating and unreliable components, this paper proposes an integrated approach to perform real-time reliability prediction for such a class of systems. For a deteriorating component, the degradation is modeled by a time-varying fault process which is a linear or approximately linear function of time. The behavior of an unreliable component is described by a random variable which has two possible values corresponding to the operating and malfunction conditions of this component. The whole proposed approach contains three algorithms. A modified interacting multiple model particle filter is adopted to estimate the dynamic system’s state variables and the unmeasurable time-varying fault. An exponential smoothing algorithm named the Holt’s method is used to predict the fault process. In the end, the system’s reliability is predicted in real time by use of the Monte Carlo strategy. The proposed approach can effectively predict the impending failure of a dynamic system, which is verified by computer simulations based on a three-vessel water tank system.     

AR-based deep learning for real-time inspection of cable brackets in aircraft

In the process of aircraft assembly, there exist numerous and ubiquitous cable brackets that shall be installed on frames and subsequently need to be manually verified with CAD models. Such a task is usually performed by special operators, hence is time-consuming, labor-intensive, and error-prone. In order to save the inspection time and increase the reliability of results, many researchers attempt to develop intelligent inspection systems using robotic, AR, or AI technologies. However, there is no comprehensive method to achieve enough portability, intelligence, efficiency, and accuracy while providing intuitive task assistance for inspectors in real time. In this paper, a combined AR+AI system is introduced to assist brackets inspection in a more intelligent yet efficient manner. Especially, AR-based Mask R-CNN is proposed by skillfully integrating markerless AR into deep learning-based instance segmentation to generate more accurate and fewer region proposals, and thus alleviates the computation load of the deep learning program. Based on this, brackets segmentation can be performed robustly and efficiently on mobile devices such as smartphones or tablets. By using the proposed system, CAD model checking can be automatically performed between the segmented physical brackets and the corresponding virtual brackets rendered by AR in real time. Furthermore, the inspection results can be directly projected on the corresponding physical brackets for the convenience of maintenance. To verify the feasibility of the proposed method, experiments are carried out on a full-scale mock-up of C919 aircraft main landing gear cabin. The experimental results indicate that the inspection accuracy is up to 97.1%. Finally, the system has been deployed in the real C919 aircraft final-assembly workshop. The preliminary evaluation reveals that the proposed real-time AR-assisted intelligent inspection approach is effective and promising for large-scale industrial applications.     

Equipment PHM using non-stationary segmental hidden semi-Markov model

Health monitoring and prognostics of equipment is a basic requirement for condition-based maintenance (CBM) in many application domains where safety, reliability, and availability of the systems are considered mission critical. As a key complement to CBM, prognostics and health management (PHM) is an approach to system life-cycle support that seeks to reduce/eliminate inspections and time-based maintenance through accurate monitoring, incipient faults. Conducting successful prognosis, however, is more difficult than conducting fault diagnosis. A much broader range of asset health related data, especially those related to the failures, shall be collected. The asset health progression can then be possibly extracted from the congregated data, which has proved to be very challenging. This paper presents a non-stationary segmental hidden semi-Markov model (NSHSMM) based prognosis method to predict equipment health. Unlike previous HSMMs, the proposed NSHSMM no longer assumes that the state-dependent transition probabilities keep the same value all the time. That is, the probability of transiting to a less healthy state does not increase with the age. “Non-stationary” means the transition probabilities will change with time. In the proposed method, in order to characterize a deteriorating equipment, three kinds of aging factor that discount the probabilities of staying at current state while increasing the probabilities of transitions to less healthy states are introduced. The performances of these aging factors are compared by using historical data colleted from three hydraulic pumps. The hazard function (h.f.) has been introduced to analyze the distribution of lifetime with a combination of historical failure data and on-line condition monitoring data. Using h.f., PHM is based on a failure rate that is a function of both the equipment age and the equipment conditions. The state values of the equipment condition considered in PHM, however, are limited to those stochastically increasing over time and those having non-decreasing effect on the hazard rate. The estimated state duration probability distributions can be used to predict the remaining useful life of the systems. With the equipment PHM, the behavior of the equipment condition can be predicted.