Sparse Autoencoder-based Multi-head Deep Neural Networks for Machinery Fault Diagnostics with Detection of Novelties

Supervised fault diagnosis typically assumes that all the types of machinery failures are known.However,in practice unknown types of defect,i.e.,novelties,may occur,whose detection is a challenging task.In this paper,a novel fault diagnostic method is developed for both diagnostics and detection of novelties.To this end,a sparse autoencoder-based multi-head Deep Neural Network(DNN)is presented to jointly learn a shared encoding representation for both unsupervised reconstruction and supervised classification of the monitoring data.The detection of novelties is based on the reconstruction error.Moreover,the computational burden is reduced by directly training the multi-head DNN with rectified linear unit activation function,instead of performing the pre-training and fine-tuning phases required for classical DNNs.The addressed method is applied to a benchmark bearing case study and to experimental data acquired from a delta 3D printer.The results show that its performance is satisfactory both in detection of novelties and fault diagnosis,outperforming other state-of-the-art methods.This research proposes a novel fault diagnostics method which can not only diagnose the known type of defect,but also detect unknown types of defects.

Time-varying fault-tolerant formation tracking based cooperative control and guidance for multiple cruise missile systems under actuator failures and directed topologies

This paper studies time-varying fault-tolerant formation tracking problems for the multiple cruise missile system under directed topologies subjected to actuator failures. Firstly, the timevarying fault-tolerant formation tracking process for the multiple cruise missile system is divided into the guidance loop and the control loop. Then protocols are constructed to accomplish distributed fault-tolerant formation tracking in the guidance loop with the adaptive updating mechanism, in the condition where neither the knowledge about actuator malfunctions nor any global information of the communication topology remains available. Moreover, sufficient conditions to accomplish formation tracking are presented, and it is shown that the multiple cruise missile system can carry on the predefined time-varying fault-tolerant control (FTC) formation tracking through the active disturbances rejection controller (ADRC) and the proportion integration (PI) controller by the way of the fault-tolerant protocol utilizing the designed strategies, in the event of actuator failures. At last, numerical analysis and simulation are designed to verify the theoretical results.

The Implementation of Fault Diagnostic Expert System for Personal Computer

In this paper a PC fault diagnostic expert system (PCDGES) is introduced, which can be run under CCDOS and encoded by English Prolog and C. In the system, a method of combining logic with production rules is applied to represent knowledge. The expert system program is separated from knowledge base. Inference computation is mainly carried backward, and the forward is regarded as an auxiliary inference. The knowledge base can be easily updated, deleted and added in operation time. It has a supporting machanism for the acquisition of knowledge and by means of “telling method”, knowledge can be acquisited. The system also has “why” explanation function and an interface with DOS, full screen editor, and hardware dignostic program. For Chinese users, all the prompt information and selection menus are displayed in color Chinese.

Observer-based adaptive control of uncertain time-delay switched systems with stuck actuator faults

This paper concerns the observer-based adaptive control problem of uncertain time-delay switched systems with stuck actuator faults. Under the case where the original controller cannot stabilize the faulty system, multiple adaptive controllers are designed and a suitable switching logic is incorporated to ensure the closed-loop system stability and state tracking. New delay-independent sufficient conditions for asymptotic stability are obtained in terms of linear matrix inequalities based on piecewise Lyapunov stability theory. On the other hand, adaptive laws for on-line updating of some of the controller parameters are also designed to compensate the effect of stuck failures. Finally, simulation results for reference [1] model show that the design is feasible and efficient.

A Model-free Approach to Fault Detection of Continuous-time Systems Based on Time Domain Data

In this paper, a model-free approach is presented to design an observer-based fault detection system of linear continuoustime systems based on input and output data in the time domain. The core of the approach is to directly identify parameters of the observer-based residual generator based on a numerically reliable data equation obtained by filtering and sampling the input and output signals.

Intelligent System for Parallel Fault-Tolerant Diagnostic Tests Construction

This investigation deals with the intelligent system for parallel fault-tolerant diagnostic tests construction. A modified parallel algorithm for fault-tolerant diagnostic tests construction is proposed. The algorithm is allowed to optimize processing time on tests construction. A matrix model of data and knowledge representation, as well as various kinds of regularities in data and knowledge are presented. Applied intelligent system for diagnostic of mental health of population which is developed with the use of intelligent system for parallel fault-tolerant DTs construction is suggested.

The Research of the Equation Model on the System-level Fault Diagnosis

In this paper we propose an equation model of system-level fault diagnoses, and construct corresponding theory and algorithms. People can turn any PMC model on ex-test into an equivalent equation (or a system of equations), and find all consistent fault patterns based on the equation model. We can also find all fault patterns, in which the fault node numbers are less than or equal to t without supposing t-diagnosable. It is not impossible for all graphic models.

Special Issue on Machine Fault Diagnostics and Prognostics

Machine components and systems, such as gears, bearings, pipes, cutting tools and turbines, may experience various types of faults, such as breakage, crack, pitting, wear, corrosion. If not being properly monitored and treated, such faults can propagate and lead to machinery perfor- mance degradation, malfunction, or even severe compo- nent/system failure. It is significant to reliably detect machinery defects, evaluate their severity, predict the fault propagation trends, and schedule optimized maintenance and inspection activities to prevent unexpected failures. Advances in these areas will support ensuring equipment and production reliability, safety, quality and productivity.

Locally Linear Back-propagation Based Contribution for Nonlinear Process Fault Diagnosis

This paper proposes a novel locally linear backpropagation based contribution(LLBBC) for nonlinear process fault diagnosis. As a method based on the deep learning model of auto-encoder(AE), LLBBC can deal with the fault diagnosis problem through extracting nonlinear features. When the on-line fault diagnosis task is in progress, a locally linear model is firstly built at the current fault sample. According to the basic idea of reconstruction based contribution(RBC), the propagation of fault information is described by using back-propagation(BP) algorithm. Then, a contribution index is established to measure the correlation between the variable and the fault, and the final diagnosis result is obtained by searching variables with large contributions. The smearing effect, which is an important factor affecting the performance of fault diagnosis, can be suppressed as well,and the theoretical analysis reveals that the correct diagnosis can be guaranteed by LLBBC. Finally, the feasibility and effectiveness of the proposed method are verified through a nonlinear numerical example and the Tennessee Eastman benchmark process.

Milling Fault Detection Method Based on Fault Tree Analysis and Hierarchical Belief Rule Base

Expert knowledge is the key to modeling milling fault detection systems based on the belief rule base.The construction of an initial expert knowledge base seriously affects the accuracy and interpretability of the milling fault detection model.However,due to the complexity of the milling system structure and the uncertainty of the milling failure index,it is often impossible to construct model expert knowledge effectively.Therefore,a milling system fault detection method based on fault tree analysis and hierarchical BRB(FTBRB)is proposed.Firstly,the proposed method uses a fault tree and hierarchical BRB modeling.Through fault tree analysis(FTA),the logical correspondence between FTA and BRB is sorted out.This can effectively embed the FTA mechanism into the BRB expert knowledge base.The hierarchical BRB model is used to solve the problem of excessive indexes and avoid combinatorial explosion.Secondly,evidence reasoning(ER)is used to ensure the transparency of the model reasoning process.Thirdly,the projection covariance matrix adaptation evolutionary strategies(P-CMA-ES)is used to optimize the model.Finally,this paper verifies the validity model and the method’s feasibility techniques for milling data sets.

Improved Relative-transformation Principal Component Analysis Based on Mahalanobis Distance and Its Application for Fault Detection

主要部件分析(PCA ) 广泛地在过程工业被使用了，它能维持最大的差错察觉率。尽管许多问题在 PCA 被处理了，一些必要问题仍然保持未解决。这研究以下列方法为差错察觉性能改进 PCA。第一，一个相对转变计划基于 Mahalanobis 距离(MD ) 被介绍消除数据的尺寸的效果而不是无尺寸的标准化，并且改进精确性和差错察觉的即时性能。理论推导证明那相对转变能直接基于 MD 消除尺寸的效果并且在结果显示出的相对空间，分析和模拟给 PCA 的合理解释它的优势和有效性。第二，一个改进摆平的预言错误(SPE ) 统计数值被给改进标准化 PCA 的差错察觉表演，它能使标准化基于 PCA 的差错察觉方法成为对实际工业过程合适的更多。最后，二个改进方法被联合更有效地检测差错。建议方法被使用在热连续滚动过程检测 looper 系统的单个差错和多差错，模拟结果以易感知，精确性和差错察觉的即时性能为差错察觉性能表明这些改进的有效性。

Rule-based Fault Diagnosis of Hall Sensors and Fault-tolerant Control of PMSM

Hall sensor is widely used for estimating rotor phase of permanent magnet synchronous motor(PMSM). And rotor position is an essential parameter of PMSM control algorithm, hence it is very dangerous if Hall senor faults occur. But there is scarcely any research focusing on fault diagnosis and fault-tolerant control of Hall sensor used in PMSM. From this standpoint, the Hall sensor faults which may occur during the PMSM operating are theoretically analyzed. According to the analysis results, the fault diagnosis algorithm of Hall sensor, which is based on three rules, is proposed to classify the fault phenomena accurately. The rotor phase estimation algorithms, based on one or two Hall sensor(s), are initialized to engender the fault-tolerant control algorithm. The fault diagnosis algorithm can detect 60 Hall fault phenomena in total as well as all detections can be fulfilled in 1/138 rotor rotation period. The fault-tolerant control algorithm can achieve a smooth torque production which means the same control effect as normal control mode (with three Hall sensors). Finally, the PMSM bench test verifies the accuracy and rapidity of fault diagnosis and fault-tolerant control strategies. The fault diagnosis algorithm can detect all Hall sensor faults promptly and fault-tolerant control algorithm allows the PMSM to face failure conditions of one or two Hall sensor(s). In addition, the transitions between health-control and fault-tolerant control conditions are smooth without any additional noise and harshness. Proposed algorithms can deal with the Hall sensor faults of PMSM in real applications, and can be provided to realize the fault diagnosis and fault-tolerant control of PMSM.

Study on Long-Distance Distributed Machine Condition Monitoring and Fault Diagnosis System

Based on the comparison of different machine condition monitoring and fault diagnosis systems, a distributed structure of on line condition monitoring and fault diagnosis with its implementation is put forward. A long distance distributed monitoring and diagnosis system is discussed in detail, and virtual reality (VR) with application in turbogenerator condition monitoring and fault diagnosis is also studied.

Reliability Analysis of Controller Area Network Based Systems—A Review

This paper reviews the research work done on the Reliability Analysis of Controller Area Network (CAN) based systems. During the last couple of decades, real-time researchers have extended schedulability analysis to a mature technique which for nontrivial systems can be used to determine whether a set of tasks executing on a single CPU or in a distributed system will meet their deadlines or not [1-3]. The main focus of the real-time research community is on hard real-time systems, and the essence of analyzing such systems is to investigate if deadlines are met in a worst case scenario. Whether this worst case actually will occur during execution, or if it is likely to occur, is not normally considered. Reliability modeling, on the other hand, involves study of fault models, characterization of distribution functions of faults and development of methods and tools for composing these distributions and models in estimating an overall reliability figure for the system [4]. This paper presents the research work done on reliability analysis developed with a focus on Controller-Area-Network-based automotive systems.

A WSN Node Fault Diagnosis Model Based on BRB with Self-Adaptive Quality Factor

Wireless sensor networks (WSNs) operate in complex and harshenvironments;thus, node faults are inevitable. Therefore, fault diagnosis ofthe WSNs node is essential. Affected by the harsh working environment ofWSNs and wireless data transmission, the data collected by WSNs containnoisy data, leading to unreliable data among the data features extracted duringfault diagnosis. To reduce the influence of unreliable data features on faultdiagnosis accuracy, this paper proposes a belief rule base (BRB) with a selfadaptivequality factor (BRB-SAQF) fault diagnosis model. First, the datafeatures required for WSN node fault diagnosis are extracted. Second, thequality factors of input attributes are introduced and calculated. Third, themodel inference process with an attribute quality factor is designed. Fourth,the projection covariance matrix adaptation evolution strategy (P-CMA-ES)algorithm is used to optimize the model’s initial parameters. Finally, the effectivenessof the proposed model is verified by comparing the commonly usedfault diagnosis methods for WSN nodes with the BRB method consideringstatic attribute reliability (BRB-Sr). The experimental results show that BRBSAQFcan reduce the influence of unreliable data features. The self-adaptivequality factor calculation method is more reasonable and accurate than thestatic attribute reliability method.

Condition-Based Diagnostic Approach for Predicting the Maintenance Requirements of Machinery

Wise maintenance-procedures are essential for achieving high industrial productivities and low energy expenditure. A major part of the energy used in any production process is expended during the maintenance of the employed equipment. To ensure plant reliability and equipment availability, a condition-based maintenance policy has been developed in this investigation. In particular, this project explored the use of vibration parameters in the diagnosis of equipment failure. A computer-based diagnostic tool employing an artificial neural-network (ANN) was developed to analyse the ensuing machinery faults, their causes and consequences. For various categories of this type of machinery, a vibration-severity chart (ISO 12372 / BS 4675: 1971) appropriately colour coded according to defined mechanical faults, was used in training of the ANN. The model was validated using data obtained from a centrifugal pump on full load and fed into the program written in Visual Basic. The results revealed that, for centrifugal pumps within 15 to 300kw power range, vibration-velocity amplitude of between 0.9 and 2.7mm/s was within acceptable limits. When the values rose to between 2.8 and 7.0mm/s, closer monitoring and improved understanding of the equipment condition was needed. The evolved diagnostic and prognostic model is applicable for other rotary equipment that is used within the same power limits.

Doping effects on the stacking fault energies of the γ' phase in Ni-based superalloys

The doping effects on the stacking fault energies(SFEs),including the superlattice intrinsic stacking fault and superlattice extrinsic stacking fault,were studied by first principles calculation of the/phase in the Ni-based superalloys.The formation energy results show that the main alloying elements in Ni-based superalloys,such as Re,Cr,Mo,Ta,and W,prefer to occupy the Al-site in Ni3 AI,Co shows a weak tendency to occupy the Ni-site,and Ru shows a weak tendency to occupy the Al-site.The SFE results show that Co and Ru could decrease the SFEs when added to fault planes,while other main elements increase SFEs.The double-packed superlattice intrinsic stacking fault energies are lower than superlattice extrinsic stacking fault energies when elements(except Co) occupy an Al-site.Furthermore,the SFEs show a symmetrical distribution with the location of the elements in the ternary model.A detailed electronic structure analysis of the Ru effects shows that SFEs correlated with not only the symmetry reduction of the charge accumulation but also the changes in structural energy.

Review: Progress in the Preparation of Iron Based Magnetic Nanoparticles for Biomedical Applications

With unique physical properties, chemical properties, and biological effects, magnetic nanomaterials are important functional materials in many fields. In the past decades, iron based magnetic nanomaterials have attracted much attention in the biomedicine field due to their superior magnetic properties and great potential in biomedical applications. In particular, magnetic iron oxide nanoparticles(MIONPs) have been playing a crucial role in the biomedicine field because of their diagnostic and therapeutic functions. Meanwhile, MIONPs are benign, low toxic, biocompatible, and biodegradable, so they are the only inorganic magnetic nanomaterials approved by the U.S. Food and Drug Administration(FDA) for clinical use at present. In this review, we mainly introduce the progress in the preparation of iron based magnetic nanomaterials for biomedical applications, including pure iron nanoparticles, iron-based alloy nanoparticles, and MIONPs, with a focus on MIONPs. Also, we summarize the preparation methods of MIONPs and point out the importance of their developments.

First-principles study of the effects of selected interstitial atoms on the generalized stacking fault energies, strength, and ductility of Ni

We analyze the influences of interstitial atoms on the generalized stacking fault energy （GSFE）, strength, and ductility of Ni by first-principles calculations. Surface energies and GSFE curves are calculated for the （112） （111） and / 101） （ 1 1 1） systems. Because of the anisotropy of the single crystal, the addition of interstitials tends to promote the strength of Ni by slipping along the （10T） direction while facilitating plastic deformation by slipping along the （115） direction. There is a different impact on the mechanical behavior of Ni when the interstitials are located in the slip plane. The evaluation of the Rice criterion reveals that the addition of the interstitials H and O increases the brittleness in Ni and promotes the probability of cleavage fracture, while the addition of S and N tends to increase the ductility. Besides, P, H, and S have a negligible effect on the deformation tendency in Ni, while the tendency of partial dislocation is more prominent with the addition of N and O. The addition of interstitial atoms tends to increase the high-energy barrier γmax, thereby the second partial resulting from the dislocation tends to reside and move on to the next layer.