Figure - available from: Advances in Mechanical Engineering
This content is subject to copyright.
Source publication
Reliability is critical for complex engineering systems. Traditionally, reliability analysis and fault diagnosis of complex engineering systems is based on reliability block diagram and fault tree. These methods are limited either on the flexibility for system characterization or on the capability for quantitative analysis. Recently, the Bayesian n...
Similar publications
In recent years, with the Chinese government’s emphasis on the development of the cold chain logistics market for fresh agricultural products, the rapid development of agricultural cold chain logistics has been promoted in many aspects. However, in the circulation of fresh agricultural products, there is still a serious problem of “broken chain” le...
The subsea all-electric Christmas tree is key equipment in subsea production systems. If a failure occurs, the marine environment will be seriously polluted. Therefore, strict reliability analysis and measures to improve reliability must be performed before such equipment is launched, which is crucial to safe subsea production. A real-time reliabil...
![Test stand of the CWRU dataset. Reproduced with permission from [27].](publication/368347801/figure/fig5/AS:11431281211963126@1702508899641/Test-stand-of-the-CWRU-dataset-Reproduced-with-permission-from-27_Q320.jpg)
In industrial systems, the vibration signals of rolling bearings are highly complex due to varying operating conditions and ambient solid noise. Facing the signals with lack of features after being disturbed by the complex environment, the traditional convolutional neural network (CNN) can not diagnose bearing faults accurately and effectively. Thi...
For the benefit of solving the problem of absoluteness of conditional probability distribution and difficulty in obtaining basic event probability in Bayesian networks, this paper studies the reliability of diesel engine cooling systems through leakage noise or gate intuitionistic fuzzy Bayesian network. Firstly, the leakage noise or gate is introd...
Citations
... As one of the popular modeling and reasoning tools, the BN model has been employed in the fields of machine learning, artificial intelligence, and uncertainty management [204]. The BN model has also been applied in the field of reliability engineering including software reliability [205], modeling maintenance [206], and fault diagnosis in systems [207,208]. Recently, the BN model was found to be effective in estimating the system/product reliability of complex systems, such as high-speed trains [208], solar-powered unmanned aerial vehicles [209], and pitting degradation structural steel in marine systems [210]. ...
... The BN model has also been applied in the field of reliability engineering including software reliability [205], modeling maintenance [206], and fault diagnosis in systems [207,208]. Recently, the BN model was found to be effective in estimating the system/product reliability of complex systems, such as high-speed trains [208], solar-powered unmanned aerial vehicles [209], and pitting degradation structural steel in marine systems [210]. ...
Light-emitting diodes (LEDs) are among the key innovations that have revolutionized the lighting industry, due to their versatility in applications, higher reliability, longer lifetime, and higher efficiency compared with other light sources. The demand for increased lifetime and higher reliability has attracted a significant number of research studies on the prognostics and lifetime estimation of LEDs, ranging from the traditional failure data analysis to the latest degradation analysis and machine learning-based approaches over the past couple of years. However, there have been few reviews that systematically address the currently evolving machine learning (ML) algorithms and methods for fault detection, diagnostics, and lifetime prediction of LEDs. To address these deficiencies, we provide a review on the diagnostic and prognostic methods and algorithms based on machine learning that helps to improve system performance, reliability, and lifetime assessment of LEDs. And the emerging trend in the application of digital twins for PHM with the focus on LEDs is also discussed. Finally, a case study on UV LED radiation degradation modeling with different machine learning methods is provided.
... As one of the popular modeling and reasoning tools, the BN model has been employed in the fields of machine learning, artificial intelligence, and uncertainty management [204]. The BN model has also been applied in the field of reliability engineering including software reliability [205], modeling maintenance [206], and fault diagnosis in systems [207,208]. Recently, the BN model was found to be effective in estimating the system/product reliability of complex systems, such as high-speed trains [208], solar-powered unmanned aerial vehicles [209], and pitting degradation structural steel in marine systems [210]. ...
... The BN model has also been applied in the field of reliability engineering including software reliability [205], modeling maintenance [206], and fault diagnosis in systems [207,208]. Recently, the BN model was found to be effective in estimating the system/product reliability of complex systems, such as high-speed trains [208], solar-powered unmanned aerial vehicles [209], and pitting degradation structural steel in marine systems [210]. ...
Nowadays, silicones are used in multiple applications. They are available as linear fluids, cyclics, gels, and resins, depending on the degree of cross-linking, or as elastomers, when fillers are incorporated in cross-linked polymers. This chapter deals with the key properties of silicones. It describes degradation behavior in terms of physical and chemical effects currently understood by detailed analysis of the aged material. With their low moisture uptake and ability to withstand harsh environmental conditions, silicone-based materials are frequently used in the electronics industry to protect fragile components against damages and corrosion.
... This conventional approach cannot cope with the AV system complexity since the system component interactions are not considered (separation principle). [43][44][45][46] Other mathematical tools, such as Petri Nets, 46-49 Markov models, 6 and BN, [50][51][52][53][54][55] are suitable for modeling and simulating complex systems. However, they require a good understanding of its component physical structure or system dynamic behavior. ...
The recent social trends and accelerated technological progress culminated in the development of autonomous vehicles (AVs). Reliability assessment for AV systems is in high demand before its market launch. In safety-critical systems (SCSs) such as AV systems, the reliability concept should be broadened to consider more safety-related issues. In this paper, reliability is defined as the probability that the system performs satisfactorily for a given period of time under stated conditions. This paper proposes a reliability assessment framework of AV, consisting of three main stages: (i) modeling the safety control structure through the Systems-Theoretic Accident Model and Processes (STAMP); (ii) mapping the control structure and functional relationships to a directed acyclic graph (DAG); and (iii) construct a Bayesian network (BN) on DAG to assess the system reliability. The fully automated (level 5) vehicle system is shown as a numeric example to illustrate how this suggested framework works. A brief discussion on involving human factors in systems to analyze lower levels of automated vehicles is also included, demonstrating the need for further research on real case studies.
... Examples include automobile failure diagnosis [11], maintenance optimization in thermal power plants [12] and severe accident simulation to predict system evolution in a sodium fast reactor [13]. Fault diagnosis has been demonstrated, as in the case of proposed models applied to a high velocity train and a subsystem of a high-power solid-state laser by mapping reliability block diagrams and fault trees, then performing diagnostic reasoning to find the main contributors to unreliability [14]. The causal approach is widely used in human-system interactions studies to handle performance-influencing factors that affect human reliability [15][16][17]. ...
Damage mechanisms that affect components within complex machines are often hard to detect and identify, especially if they are difficult to access, inspect and/or that are under continuous duty, compromising the reliability and performance of systems. In this paper, a Bayesian network model is developed to handle the interactions among common damage mechanisms and failure modes in nuclear steam turbine rotating blades. This model enables maintenance and inspection planning to better predict which portions(s) of the turbine will need repair. To compute the conditional probability tables, the model's unique quantification method combines expert judgement, the Recursive Noisy OR, and a damage mechanism susceptibility ranking that takes into account the synergistic interactions of the damage mechanisms. The approach can be suited to different turbine designs and purposes. The Bayesian network model development is described in detail, validated, and several examples of its application are presented.
... As one of the popular modelling and reasoning tools, the BN model has been employed in the fields of machine learning, artificial intelligence, and uncertainty management [33]. The BN model has also been applied in the field of reliability engineering including software reliability [34], modelling maintenance [35], and fault diagnosis in systems [36,37]. Recently, the BN model was found to be effective in estimating the system/product reliability of complex systems, such as high-speed trains [37], solar-powered unmanned aerial vehicles [38] and pitting degradation structural steel in marine systems [39]. ...
... The BN model has also been applied in the field of reliability engineering including software reliability [34], modelling maintenance [35], and fault diagnosis in systems [36,37]. Recently, the BN model was found to be effective in estimating the system/product reliability of complex systems, such as high-speed trains [37], solar-powered unmanned aerial vehicles [38] and pitting degradation structural steel in marine systems [39]. Zheng et al. [40] presented an improved compression inference algorithm in multilevel BN to analyze the reliability of complex multistate satellite systems. ...
The increased system complexity in electronic products brings challenges in a system level reliability assessment and lifetime estimation. Traditionally, the graph model-based reliability block diagrams (RBD) and fault tree analysis (FTA) have been used to assess the reliability of products and systems. However, these methods are based on deterministic relationships between components that introduce prediction inaccuracy. To fill the gap, a Bayesian Network (BN) method is introduced that considers the intricacies of the high-power light-emitting diode (LED) lamp system and the functional interaction among components for reliability assessment and lifetime prediction. An accelerated degradation test was conducted to analyze the evolution of the degradation and failure of components that influence the system level lifetime and performance of LED lamps. The Gamma process and Weibull distribution are used for component level lifetime prediction. The junction tree algorithm was deployed in the BN structure to estimate the joint probability distributions of the lifetime states. The degradation and prediction results showed that LED modules contribute a major part for lumen degradation of LED lamps followed by drivers and the least effect is from diffuser and reflector. The BN based lifetime estimation results also exhibited an accurate prediction as validated with the Gamma process and such improved reliability assessment outcomes are beneficial to LED manufacturers and customers. Thus, the proposed approach is effective to evaluate and address the long-term reliability assessment concerns of high-reliability LED lamps and fulfill the guarantee of high prediction accuracy in less time and cost-effective manner.
... en, domestic and foreign scholars continued to improve it. Bayesian networks have been widely used in machinery [4][5][6][7], electric power [8][9][10][11], civil engineering [12][13][14], nuclear technology [15,16], communications [17,18], and other fields for system reliability analysis [4,19], safety analysis [20], and fault diagnosis of key units [21]. For the reliability analysis of multistate systems, Wilson [22] and Graves et al. [23] studied the method of applying BNs to establish a multistate system model. ...
This study focused on mixed uncertainty of the state information in each unit caused by a lack of data, complex structures, and insufficient understanding in a complex multistate system as well as common-cause failure between units. This study combined a cloud model, Bayesian network, and common-cause failure theory to expand a Bayesian network by incorporating cloud model theory. The cloud model and Bayesian network were combined to form a reliable cloud Bayesian network analysis method. First, the qualitative language for each unit state performance level in the multistate system was converted into quantitative values through the cloud, and cloud theory was then used to express the uncertainty of the probability of each state of the root node. Then, the β-factor method was used to analyze reliability digital characteristic values when there was common-cause failure between the system units and when each unit failed independently. The accuracy and feasibility of the method are demonstrated using an example of the steering hydraulic system of a pipelayer. This study solves the reliability analysis problem of mixed uncertainty in the state probability information of each unit in a multistate system under the condition of common-cause failure. The multistate system, mixed uncertainty of the state probability information of each unit, and common-cause failure between the units were integrated to provide new ideas and methods for reliability analysis to avoid large errors in engineering and provide guidance for actual engineering projects.
... [215] The BN model has also been applied in the field of reliability engineering including software reliability, [216] modeling maintenance, [217] and fault diagnosis in systems. [218,219] Recently, the BN model was found to be effective in estimating the system/product reliability of complex systems, such as high-speed trains, [219] solar-powered unmanned aerial vehicles, [220] and pitting degradation structural steel in marine systems. [221] In this section, a BN method that considers the intricacies of the high-power LED lamp system and the functional interaction among components for reliability assessment and lifetime prediction is briefly introduced. ...
... [215] The BN model has also been applied in the field of reliability engineering including software reliability, [216] modeling maintenance, [217] and fault diagnosis in systems. [218,219] Recently, the BN model was found to be effective in estimating the system/product reliability of complex systems, such as high-speed trains, [219] solar-powered unmanned aerial vehicles, [220] and pitting degradation structural steel in marine systems. [221] In this section, a BN method that considers the intricacies of the high-power LED lamp system and the functional interaction among components for reliability assessment and lifetime prediction is briefly introduced. ...
Light‐emitting diodes (LEDs) are among the key innovations that have revolutionized the lighting industry, due to their versatility in applications, higher reliability, longer lifetime, and higher efficiency compared with other light sources. The demand for increased lifetime and higher reliability has attracted a significant number of research studies on the prognostics and lifetime estimation of LEDs, ranging from the traditional failure data analysis to the latest degradation modeling and machine learning based approaches over the past couple of years. However, there is a lack of reviews that systematically address the currently evolving machine learning algorithms and methods for fault detection, diagnostics, and lifetime prediction of LEDs. To address those deficiencies, a review on the diagnostic and prognostic methods and algorithms based on machine learning that helps to improve system performance, reliability, and lifetime assessment of LEDs is provided. The fundamental principles, pros and cons of methods including artificial neural networks, principal component analysis, hidden Markov models, support vector machines, and Bayesian networks are presented. Finally, a discussion on the prospects of the machine learning implementation from LED packages, components to system level reliability analysis, potential challenges and opportunities, and the future digital twin technology for LEDs lifetime analysis is provided.
... Reliability of fault diagnoses analysis for complex engineering system is based traditionally on reliability of fault tree diagram which is limited methods. It has been demonstrated that Bayesian network method, has a great flexibility and it has been introduced into reliability engineering category [6]. In [7] are studied cause of gas leakage and the accidents triggered by gas leakage, using bow-tie analysis and Bayesian network, in order to confirm critical nodes of accidents introducing three measures: Birnbaum measure, risk achievement worth and Fussel-Vesely. ...
The trend of SCADA (Supervisory Control and Data Acquisition) is to deploy in Cloud Computing domain and have as main advantage reducing the costs and removing the local hardware and software infrastructure. The most common method of communication between SCADA sites and Cloud servers is GSM (Global System for Mobile Communication) network. Process plant placed in the field involve sometimes quick decisions in order to avoid hazard or malfunctioning processes. In these cases, the GSM communication support is not a convenient solution, due to the latency of the data transfer. When the result of data analysis requires immediate action and higher levels must be accessed as Cloud, a server installing into local architecture, able to communicate to the Cloud server is a solution called Fog Computing. The concept of Fog Computing has emerged due to data latency in Cloud Computing servers. The article presents a solution for detecting hazardous situations, possible to occur in the biogas production area of a Wastewater Treatment Plant. The information is sent from the sensors via PLCs to the Fog Computing server as tags on OPC protocol. The data are analyzed using the Bayesian algorithm and has the effect warning the operating personnel about the imminence of a dangerous situation. A field maintenance control is requiring.
... Due to the increasing complexity of engineering systems, the identification and evaluation of risks associated with the failure of individual components is usually the starting point for efficient reliability and safety analysis. For this purpose, several advanced techniques such as Fault Tree Analysis (FTA), Failure Mode and Effects Analysis (FMEA), Reliability Block Diagram (RBD), Reliability-Centered Maintenance (RCM), Monte-Carlo Simulation (MCS), Markov Analysis (MA) and Bayesian Networks (BN) have been developed in the literature [2][3][4]. ...
Engineering systems such as energy production facilities, aviation systems, maritime vessels, etc. continue to grow in size and complexity. This growth has made the identification, quantification and mitigation of risks associated with the failure of such systems so complicated. To solve this problem, several advanced techniques such as Fault Tree Analysis (FTA), Failure Mode and Effects Analysis (FMEA), Reliability-Block Diagram (RBD), Reliability-Centered Maintenance (RCM), Monte-Carlo Simulation (MCS), Markov Analysis (MA) and Bayesian Networks (BN) have been developed in the literature. In order to improve the strengths and eliminate the drawbacks of classical techniques, some hybrid models have been recently developed. In this paper, an integrated FTA and FMEA model is proposed for risk analysis of safety-critical systems. Minimal cut sets derived from the fault trees are weighted based on Birnbaum’s measure of importance and then the weights are used to revise Risk Priority Numbers (RPNs) obtained from the use of traditional FMEA techniques. The proposed model is applied to a Blowout Preventer (BOP) system operating under erratic and extreme conditions in a subsea oil and gas field. Though those failures caused by kill valves and hydraulic lines remain among the top risks in the BOP system, significant differences are revealed in risk rankings when the results from the hybrid approach are compared with those obtained from the classical risk analysis methods.
... Therefore, how to identify fault types is still the most challenging part of robot control optimization. Traditional fault diagnosis is analyzed by skilled engineers in time domain [2], which is difficult and time-consuming, especially in the case of large samples and/or high-dimensional samples. With the increase of data size, analysis becomes quite complex. ...
In order to realize automation of the pollutant emission tests of vehicles, a pedal robot is designed instead of a human-driven vehicle. Sometimes, the actual time-speed curve of the vehicle will deviate from the upper or lower limit of the worldwide light-duty test cycle (WLTC) target curve, which will cause a fault. In this paper, a new fault diagnosis method is proposed and applied to the pedal robot. Since principal component analysis (PCA), t-distributed stochastic neighbor embedding (t-SNE), and Autoencoder cannot extract feature information adequately when they are used alone, three types of feature components extracted by PCA, t-SNE, and Autoencoder are fused to form a nine-dimensional feature set. Then, the feature set is reduced into three-dimensional space via Treelet Transform. Finally, the fault samples are classified by Gaussian process classifier. Compared with the methods using only one algorithm to extract features, the proposed method has the minimum standard deviation, 0.0078, and almost the maximum accuracy, 98.17%. The accuracy of the proposed method is only 0.24% lower than that without Treelet Transform, but the processing time is 6.73% less than that without Treelet Transform. These indicate that the multi-features fusion model and Treelet Transform method is quite effective. Therefore, the proposed method is quite helpful for fault diagnosis of the pedal robot.
