Faulty States Research Articles

Fault Detection for Wind Turbine System Using Fractional Extended Dispersion Entropy and Cumulative Sum Control Chart

Reliable and quick fault detection is crucial for the wind turbine system (WTS) to detect any potential abnormalities and early faults in time. However, constructing sensitive indicators to reflect the operation state of WTS is still a challenging work. In view of the conceptions of fractional calculus and dispersion entropy, this paper proposes a novel indicator called fractional extended dispersion entropy (FrEDE) to cope with the challenge. Specifically, a connection block with an information factor is first applied to enhance the utilization of information in the raw signals. Moreover, fractional calculus is integrated into entropy calculation to support a constructive interplay in the fault detection of complex WTS. The experiments on simulated data investigate the effect of parameters on FrEDE and verify its ability to detect the dynamic changes of complex system. Finally, FrEDE is further applied to two real-world datasets. Comparative experimental results show that FrEDE is able to accurately differentiate normal between faulty states, and a detection scheme fusing FrEDE and cumulative sum control chart (CUSUM) is accessible to detect abnormal stats and provide early failure alarm effectively.

Fault Diagnosis of HTS–SLIM Based on 3D Finite Element Method and Hilbert–Huang Transform

The Linear Induction Motors (LIMs) are a novel structure of industrial motors, which have appeared in recent years. There are various models of optimal LIMs that help better performance. However, no research could be found about the behavior of these motors under the fault conditions. In this paper, a High–Temperature Superconducting Single–sided LIM (HTS–SLIM), with flat–solid secondary sheet is considered. Besides, a comprehensive review of novel and robustness fault diagnosis methods in electrical machines is carried out. To satisfy the paper aims, two mechanical and electrical failures, in forms of broken conductor sheet and short–circuit of coil are considered, respectively, and the dynamic model of the studied motor under short–circuit fault is proposed. The motor is modeled with 3D Finite Element Method (FEM), in order to consider the 3D effects of linear motors. Finally, the electromagnetic and mechanical behaviors of the considered machine are rendered under various conditions. The variation of various parameters are studied and their increament or decreament under faulty states are analyzed. In the next step, the Hilbert–Huang Transform (HHT) is employed to detect the features of the mentioned faults. The results and analysis show that the thrust and speed of motor have decreased under short circuit faults, and they have increased suddenly, when the primary cross over the broken secondary sheet about 600 % and 43 %, respectively. Besides, the flux density of all components under short circuit is reduced, while it increased under broken sheet fault and when these faults occur simultaneously.

СПЕКТРАЛЬНИЙ АНАЛІЗ СИГНАЛУ ВІБРАЦІЇ З ВИКОРИСТАННЯМ ПЕРЕТВОРЕННЯ ФУР’Є

The paper analyzes the topical issue of timely detection and prevention of a dangerous state of critical machines and mechanisms using vibration diagnostics as a promising method. It is proposed to use the method of analysis of vibration spectra in order to identify malfunctions, by processing the output signal from the sensor, which is sent to a personal computer, where a spectral analysis of the measured vibration signal is performed using a diagnostic program based on MATLAB. It is proposed to use spectral analysis, which is a traditional method of vibration diagnostics. It is supposed to determine the faulty state according to vibration measurement data and then to determine the nature of the fault according to the vibration signals analysis using the Fourier transform. It is proposed to process the output signal from the vibration sensor to a personal computer, where a spectral analysis of the measured vibration signal is carried out using a diagnostic program based on MATLAB. The use of FFT algorithms is due to a decrease in the number of operations performed, and, consequently, an increase in performance. It is shown that the decomposition of a complex signal in a Fourier series gives the components of the spectrum, which are, in narrow-band analysis, the harmonic components of the complex signal. It has been determined that narrowband spectral analysis allows detecting a larger number of faults or defects and is used for monitoring and in-depth diagnostics of equipment. Knowing the frequencies at which malfunctions of the kinematic pairs of machinery are manifested, the amplitude of the spectrum components can be used to assess their state. It was determined that spectral analysis is widely used in the processing of vibration diagnostics data, being the main and classical method of analysis. To optimize the duration of the test, it is necessary to take into account the relationship between the spectrum bandwidth and the signal accumulation time. The pass-through characteristic reflects the dependence of the signal level on time at a certain frequency, illustrating the process of signal accumulation during narrow-band spectral analysis. The narrower the analysis strip, the longer the measurements take.

Class-Imbalance Adversarial Transfer Learning Network for Cross-Domain Fault Diagnosis With Imbalanced Data

Recently, cross-domain fault diagnosis based on transfer learning methods has been extensively explored and well-addressed when class-balance data with supervision information are available. However, data under machine faulty states are mostly difficult to collect; there is a huge divide between current transfer learning methods based on implicit class-balance data and real industrial applications. In this article, we propose a class-imbalance adversarial transfer learning (CIATL) network with input being imbalanced data to learn domain-invariant and knowledge. Within this framework, class-imbalance learning is embedded into the adversarial training process to learn class-separate diagnostic knowledge with imbalanced data, double-level adversarial transfer learning including marginal and conditional distribution adaptations is conducted to learn domain-invariant knowledge. Extensive experiments on a planetary gearbox rig with imbalanced data verify the effectiveness and generalization of the proposed method and show its superior performance over contrastive transfer learning methods. Moreover, the proposed method relaxes the underlying assumption that the success of current transfer learning regimes is rooted in class-balance data and extends the application of the transfer learning method for real-industrial cross-domain diagnosis tasks.

Bayesian Optimization LSTM/bi-LSTM Network With Self-Optimized Structure and Hyperparameters for Remaining Useful Life Estimation of Lathe Spindle Unit

Abstract An effective maintenance strategy to cut back maintenance costs and production loss with assured product quality has always been a major concern for industries. The Industry 4.0 era has built a wide acceptance for the predictive maintenance techniques in the remaining useful life (RUL) estimation of critical industrial systems. In this paper, long short-term memory (LSTM) and bidirectional-LSTM (bi-LSTM) deep neural architecture-based predictive algorithms are proposed for the RUL estimation of the lathe spindle unit. The deep learning algorithm is embedded within a Bayesian optimization algorithm for the self-optimization of its network structure and hyperparameters. The proposed deep learning algorithm is trained using lathe spindle health degradation data collected from an experimental accelerated run-to-failure test rig to evolve an RUL prediction model. The vibration signals representing lathe spindle health degradation from the health to faulty state are analyzed to extract time, frequency, and time-frequency domain features, which are then subjected to a neighborhood component analysis (NCA) based feature selection criteria. Finally, the selected relevant features are used to train the optimized LSTM/bi-LSTM network for RUL estimation. A comparison of the prediction results for Bayesian optimized LSTM/bi-LSTM network architectures and other prominent data-driven approaches are performed. The Bayesian optimized LSTM + bi-LSTM deep network architecture is observed to have the highest prediction accuracy for lathe spindle RUL estimation.

Machinery Faults Prediction Using Ensemble Tree Classifiers: Bagging or Boosting?

One of the main goals of predictive maintenance is to accurately classify the temporal trends as early as possible, detect faulty states and pinpoint the root cause of the fault. Undoubtedly, neither late nor early maintenance is desirable and incurs additional operating costs; however, early identification of faulty trends and scheduling on-time maintenance is crucial to smooth machinery operation. Various data-driven techniques have been used to identify faults; nevertheless, many of these techniques fail to perform when faced with missing values at run time or lack any explanation on the root cause of the fault. The present work offers a comprehensive study on different techniques used for fault type classification and compares their performance in identifying the mode of operation for the PHME21 dataset. We also evaluate the robustness of such classifiers against missing values. This study shows that tree-based techniques are best suited to perform root cause analysis for each faulty state and establish rules for faulty conditions.

An Expert System for Rotating Machine Fault Detection Using Vibration Signal Analysis.

Accurate and early detection of machine faults is an important step in the preventive maintenance of industrial enterprises. It is essential to avoid unexpected downtime as well as to ensure the reliability of equipment and safety of humans. In the case of rotating machines, significant information about machine’s health and condition is present in the spectrum of its vibration signal. This work proposes a fault detection system of rotating machines using vibration signal analysis. First, a dataset of 3-dimensional vibration signals is acquired from large induction motors representing healthy and faulty states. The signal conditioning is performed using empirical mode decomposition technique. Next, multi-domain feature extraction is done to obtain various combinations of most discriminant temporal and spectral features from the denoised signals. Finally, the classification step is performed with various kernel settings of multiple classifiers including support vector machines, K-nearest neighbors, decision tree and linear discriminant analysis. The classification results demonstrate that a hybrid combination of time and spectral features, classified using support vector machines with Gaussian kernel achieves the best performance with 98.2% accuracy, 96.6% sensitivity, 100% specificity and 1.8% error rate.

Knowledge Modeling in Troubleshooting

Introduction. The article describes the approach to solving the problem of complex technical system troubleshooting based on expert knowledge modeling. Intelligent information systems are widely used to solve the problems of diagnostics of multilevel systems including combine harvesters. The formal description of the subject domain knowledge is the framework for building the knowledge base of these systems. The sequence of creating an expert system knowledge base in accordance with production rules is considered. Materials and Methods. The approach is founded on the fault function table. As the object of diagnostics, one of the subsystems of the combine harvester electric equipment “opening the hopper roof flaps” is considered. The basis for constructing a sequence of elementary checks is a system of logical equations describing both the serviceable and possible faulty states of the subsystem. Results. A structural logic model is developed. As a result of analyzing the fault function table, the sets of elementary checks are determined. Four criteria have been used to analyze the weight of these checks. The authors have determined optimal sequence of checks and have developed a decision tree, which allows finding the cause of the malfunction and is the basis for creating the knowledge base of an intelligent information system. A fragment of the knowledge base is given. Discussion and Conclusion. The proposed approach of expert knowledge modelling increases the efficiency of the unit for troubleshooting of the intelligent decision support system. It makes possible to structure the base of expertise and establishing the optimal sequence of elementary checks. This allows determining the optimal sequence of application of the knowledge base production rule that makes it possible to reduce the time of restoring the serviceability of combines.

Transparent memory tests with even repeating addresses for storage devices

The urgency of the problem of memory testing of modern computing systems is shown. Mathematical models describing the faulty states of storage devices and the methods used for their detection are investigated. The concept of address sequences (pA) with an even repetition of addresses is introduced, which are the basis of the basic element included in the structure of the new transparent march tests March _pA_1 and March _pA_2. Algorithms for the formation of such sequences and examples of their implementations are given. The maximum diagnostic ability of new tests is shown for the case of the simplest faults, such as constant (SAF) and transition faults (TF), as well as for complex pattern sensitive faults (PNPSFk). There is a significantly lower time complexity of the March_pA_1 and March_pA_2 tests compared to classical transparent tests, which is achieved at the expense of less time spent on obtaining a reference signature. New distance metrics are introduced to quantitatively compare the effectiveness of the applied pA address sequences in a single implementation of the March_pA_1 and March_pA_2 tests. The basis of new metrics is the distance D(A(j), pA) determined by the difference between the indices of repeated addresses A(j) in the sequence pA. The properties of new characteristics of the pA sequences are investigated and their applicability is evaluated for choosing the optimal test pA sequences that ensure the high efficiency of new transparent tests. Examples of calculating distance metrics are given and the dependence of the effectiveness of new tests on the numerical values of the distance metrics is shown. As well as in the case of classical transparent tests, multiple applications of new March_pA_1 and March_pA_2 tests are considered. The characteristic V(pA) is introduced, which is numerically equal to the number of different values of the distance D(A(j), pA) of addresses A(j) of the sequence pA. The validity of analytical estimates is experimentally shown and high efficiency of fault detection by the tests March_pA_1 and March_pA_2 is confirmed by the example of coupling faults for p = 2.

Fault Injection Model of Induction Motor for Stator Interturn Fault Diagnosis Research Based on HILS

Recently, in order to ensure the reliability and safety of trains, online condition monitoring and fault diagnosis of traction induction motors have become active issues in the area of rail transportation. The fault diagnosis algorithm can be developed and debugged in a real-time environment based on hardware-in-the-loop simulation (HILS). However, the dynamic space model of induction motors with stator interturn short-circuit faults faces the problem that the faulty state and the healthy state are not compatible, which is inconvenient for the HILS. In this paper, a fault injection model is proposed for the first time, which can realize the online switching between the healthy state and the faulty state of the motor. The feasibility and effectiveness of the proposed model are verified by simulation experiments the based on MATLAB/Simulink and dSPACE HILS platforms.

Autonomous Assessment of Delamination Using Scarce Raw Structural Vibration and Transfer Learning.

Deep learning has helped achieve breakthroughs in a variety of applications; however, the lack of data from faulty states hinders the development of effective and robust diagnostic strategies using deep learning models. This work introduces a transfer learning framework for the autonomous detection, isolation, and quantification of delamination in laminated composites based on scarce low-frequency structural vibration data. Limited response data from an electromechanically coupled simulation model and from experimental testing of laminated composite coupons were encoded into high-resolution time-frequency images using SynchroExtracting Transforms (SETs). The simulated and experimental data were processed through different layers of pretrained deep learning models based on AlexNet, GoogleNet, SqueezeNet, ResNet-18, and VGG-16 to extract low- and high-level autonomous features. The support vector machine (SVM) machine learning algorithm was employed to assess how the identified autonomous features were able to assist in the detection, isolation, and quantification of delamination in laminated composites. The results obtained using these autonomous features were also compared with those obtained using handcrafted statistical features. The obtained results are encouraging and provide a new direction that will allow us to progress in the autonomous damage assessment of laminated composites despite being limited to using raw scarce structural vibration data.

Application Combining VMD and ResNet101 in Intelligent Diagnosis of Motor Faults.

Motor failure is one of the biggest problems in the safe and reliable operation of large mechanical equipment such as wind power equipment, electric vehicles, and computer numerical control machines. Fault diagnosis is a method to ensure the safe operation of motor equipment. This research proposes an automatic fault diagnosis system combined with variational mode decomposition (VMD) and residual neural network 101 (ResNet101). This method unifies the pre-analysis, feature extraction, and health status recognition of motor fault signals under one framework to realize end-to-end intelligent fault diagnosis. Research data are used to compare the performance of the three models through a data set released by the Federal University of Rio de Janeiro (UFRJ). VMD is a non-recursive adaptive signal decomposition method that is suitable for processing the vibration signals of motor equipment under variable working conditions. Applied to bearing fault diagnosis, high-dimensional fault features are extracted. Deep learning shows an absolute advantage in the field of fault diagnosis with its powerful feature extraction capabilities. ResNet101 is used to build a model of motor fault diagnosis. The method of using ResNet101 for image feature learning can extract features for each image block of the image and give full play to the advantages of deep learning to obtain accurate results. Through the three links of signal acquisition, feature extraction, and fault identification and prediction, a mechanical intelligent fault diagnosis system is established to identify the healthy or faulty state of a motor. The experimental results show that this method can accurately identify six common motor faults, and the prediction accuracy rate is 94%. Thus, this work provides a more effective method for motor fault diagnosis that has a wide range of application prospects in fault diagnosis engineering.

Determination of Diagnostic Parameters of Power Plants Based on Internal Combustion Engines

Abstract The presented article shows a method for finding monitored parameters for creating a diagnostic system for autonomous power sources based on spark ignition engines and diesel engines. The classification of structures of autonomous power sources based on internal combustion engines has been carried out. The analysis of the design features of the most common back-up power sources on the market based on internal combustion engines (ICE) indicates the widespread use of generators with a synchronous alternator. The analysis of the design features of autonomous power supplies has made it possible to develop logical models for different designs. The influence of the occurrence of a faulty state of each element on other elements of the systems is analyzed, and the results of the analysis are summarized in tables. An informative Claude Chenon criterion is proposed for finding the optimal number of diagnostic parameters among an infinite number of possible combinations of physical parameters that characterize the system. When solving the problem, a hypothesis was proposed about the equiprobability of cases of exit from the working state of each of the elements of the system. The use of Claude Chenon allows you to find the parts that make up the generators, which with maximum efficiency reduce the degree of uncertainty in the system. After determining the residual entropy, the parts of the system are selected, the state of which should be monitored by the diagnostic system. For such parts of the system, diagnostic parameters are found and methods for obtaining them are indicated.

Influence of a Winding Short-Circuit Fault on Demagnetization Risk and Local Magnetic Forces in V-Shaped Interior PMSM with Distributed and Concentrated Winding

This paper presents a comparison of 30/8 and 12/8 AC permanent magnet motors with distributed (DW) and concentrated winding (CW) designed for electric vehicle traction. Both prototypes are based on an interior permanent magnet (IPM) motor topology and contain V-shape magnets. The radial flux AC IPM motors were designed for an 80 kW propulsion system to achieve 125 N·m. Finite element models (FEM) used to design the geometry of IPM motors and the required useful parameters of electric motors are widely investigated. The accuracy of finite element models is verified and validated on the basis of test data. Numerical simulations of healthy and faulty operation states, and studies of winding faults based on the FEM offer a deeper understanding of the associated phenomena. Therefore, in this paper, a short-circuit fault in a stator winding was simulated to investigate the transient currents under an external load collapse, for all winding phases. These simulations were used to define other important machine parameters to improve mechanical reliability of the motors and to assess the potential risk of permanent magnet (PM) demagnetization. Furthermore, the analysis of local magnetic forces affecting the PMs in the rotor and their possible displacement in a short-circuit situation were performed, also taking into account the centrifugal force. Lastly, it is demonstrated that the choice of winding configuration has a significant impact on the uncontrolled displacement of magnets in the rotor.

The digital twin in Industry 4.0: A wide‐angle perspective

AbstractThe move towards advanced manufacturing and Industry 4.0 is fed by increased demand for speeding up innovation, increasing flexibility, improving maintenance, and becoming more customized while saving on the total cost of operations. This is accompanied by increased dependence on virtual product and process development, data‐driven processes, and product knowledge. Other characteristics, affecting modern design, include big data intelligence in product, process, and maintenance. New technologies that empower data analytics include added manufacturing, flexible manufacturing, robotics, sensor technology, smart value/supply chains, and industrial information backbones. This paper is about surrogate models, also called digital twins, that provide an important complementary capacity to physical assets. Digital twins capture past, present, and predicted behavior of physical assets. Digital twin models are updated periodically to represent the current state of physical assets. This distinguishes digital twins from conventional simulations in that sensor data can continuously feed them. The type of curated information on the state of physical asset's history depends on how digital twins are used. For example, if a digital twin is used for fault classification, the history captured is operational data from equipment in healthy and faulty states. We provide here a review of digital twins, with an emphasis on Industry 4.0 applications.

Real-Time Fault Detection in Discrete Manufacturing Systems Via LSTM Model based on PLC Digital Control Signals

A lot of sensor and control signals is generated by an industrial controller and related internet-of-things in discrete manufacturing system. The acquired signals are such records indicating whether several process operations have been correctly conducted or not in the system, therefore they are usually composed of binary numbers. For example, once a certain sensor turns on, the corresponding value is changed from 0 to 1, and it means the process is finished the previous operation and ready to conduct next operation. If an actuator starts to move, the corresponding value is changed from 0 to 1 and it indicates the corresponding operation is been conducting. Because traditional fault detection approaches are generally conducted with analog sensor signals and the signals show stationary during normal operation states, it is not simple to identify whether the manufacturing process works properly via conventional fault detection methods. However, digital control signals collected from a programmable logic controller continuously vary during normal process operation in order to show inherent sequence information which indicates the conducting operation tasks. Therefore, in this research, it is proposed to a recurrent neural network-based fault detection approach for considering sequential patterns in normal states of the manufacturing process. Using the constructed long short-term memory based fault detection, it is possible to predict the next control signals and detect faulty states by compared the predicted and real control signals in real-time. We validated and verified the proposed fault detection methods using digital control signals which are collected from a laser marking process, and the method provide good detection performance only using binary values.

A Comparison Study of Data-Driven Anomaly Detection Approaches for Industrial Chillers

Faults in industrial chiller systems can lead to higher energy consumption, increasing wear of system components and shorten equipment life. While they gradually cause anomalous system operating conditions, modern automatic fault detection models aim to detect them at low severity by using real-time sensor data. Many scientific contributions addressed this topic in the past and presented data-driven approaches to detect faulty system states. Although many promising results were presented to date, there is lack of suitable comparison studies that show the effectiveness of the proposed models by use of data stemming from different chiller systems. Therefore this study aims at detecting a suitable data-driven approach to detect faults reliable in different domains of industrial chillers. Thus, a unified procedure is developed, to train all algorithms in an identical way with same data-basis. Since most of the reviewed papers used only one dataset for training and testing, the selected approaches are trained and validated on two different datasets from real refrigeration systems. The data-driven approaches are evaluated based on their accuracy and true negative rate, from which the most suitable approach is derived as a conclusion.

Environmental safety diagnosis and maintenance specific of heavy vehicles and buses engines functioning with compressed natural gas

The results of a statistical survey of the content of toxic components CO, CH and NOX in the exhaust gases of 38 “LiAZ” buses (4th and 5th ecological classes with foreign-made engines) at the nominal and increased engine crankshaft rotation speeds in idle running at compressed (compressed) natural gas in Moscow and adjacent areas of the region. It has been established that, as a first approximation, these modes provide information on the deterioration of environmental safety, primarily in relation to nitrogen oxide (NOx) emissions, the control of which in ordinary operation by the existing technical regulations for all types of vehicles, including heavy-duty gas vehicles are not provided. Statistical processing, with an assessment of the maximum permissible value of this diagnostic parameter in two idle modes (no more than 50 M-1 for the best attainable states of buses of the 5th ecological class), showed that the absence of such a simple control leads to approximately 75% of faulty states. These indicators can be significantly improved with the introduction of monitoring of operational monitoring of NOx and the development of more complex maintenance technologies. Herewith there is a significant environmental safety improvement of gas motor buses in comparison with diesel versions (approx. 6-8 times) and the technological and economic feasibility of their use for many regions of the country. Preliminary studies of the structure of such a technology have been carried out on a “KAMAZ” gas vehicle, which has an engine control different from “LiAZ” buses. At the same time, the higher NOX emissions level could be considered as allowable for intercity bus transportation and for activities outside the city, however, they can be reduced by about 3…5 times due to the use of the latest versions of pre-chamber devices “Ball Lightning”.

Unsupervised Fault Detection on Unmanned Aerial Vehicles: Encoding and Thresholding Approach.

Unmanned Aerial Vehicles are expected to create enormous benefits to society, but there are safety concerns in recognizing faults at the vehicle’s control component. Prior studies proposed various fault detection approaches leveraging heuristics-based rules and supervised learning-based models, but there were several drawbacks. The rule-based approaches required an engineer to update the rules on every type of fault, and the supervised learning-based approaches necessitated the acquisition of a finely-labeled training dataset. Moreover, both prior approaches commonly include a limit that the detection model can identify the trained type of faults only, but fail to recognize the unseen type of faults. In pursuit of resolving the aforementioned drawbacks, we proposed a fault detection model utilizing a stacked autoencoder that lies under unsupervised learning. The autoencoder was trained with data from safe UAV states, and its reconstruction loss was examined to distinguish the safe states and faulty states. The key contributions of our study are, as follows. First, we presented a series of analyses to extract essential features from raw UAV flight logs. Second, we designed a fault detection model consisting of the stacked autoencoder and the classifier. Lastly, we validated our approach’s fault detection performance with two datasets consisting of different types of UAV faults.

System integration for predictive process adjustment and cloud computing-based real-time condition monitoring of vibration sensor signals in automated storage and retrieval systems

As automation and digitalization are being increasingly implemented in industrial applications, manufacturing systems comprising several functions are becoming more complex. Consequently, fault analysis (e.g., fault detection, diagnosis, and prediction) has attracted increased research attention. Investigations involving fault analysis are usually performed using real-time, online, or automated techniques for fault detection or alarming. Conversely, recovery of faulty states to their healthy forms is usually performed manually under offline conditions. However, the development of intelligent systems requires that appropriate feedback be provided automatically, to facilitate faulty-state recovery without the need for manual operator intervention and/or decision-making. To this end, this paper proposes a system integration technique for predictive process adjustment that determines appropriate recovery actions and performs them automatically by analyzing relevant sensor signals pertaining to the current situation of a manufacturing unit via cloud computing and machine learning. The proposed system corresponds to an automated predictive process adjustment module of an automated storage and retrieval system (ASRS). The said integrated module collects and analyzes the temperature and vibration signals of a product transporter using an internet-of-things-based programmable logic controller and cloud computing to identify the current states of the ASRS system. Upon detection of faulty states, the control program identifies corresponding process control variables and controls them to recover the system to its previous no-fault state. The proposed system will facilitate automatic prognostics and health management in complex manufacturing systems by providing automatic fault diagnosis and predictive recovery feedback.