Faulty Conditions Research Articles

Requirements and Data Integrity Considerations for Diagnostics Testbeds

The process of generating high quality data for the test and evaluation of diagnostic and prognostic algorithms is still of high importance to the Prognostics and Health Management (PHM) research community. To support these efforts a testbed has been designed, manufactured and commissioned. It has specifically been designed in order to replicate several component degradation faults with high accuracy and high repeatability. This paper documents the design, requirements and the data integrity elements of this benchmark hydraulic system. This document consolidates the process of designing diagnostics testbeds as at present there is a lack of literature on how diagnostics testbeds should be built and is intended to serve as a starting point and quick reference guide for engineers and researchers intending to design and develop a testbed to test and validate PHM applications. The first part of this paper highlights design requirements for all the design aspects for such testbeds with great consideration for industry standards and best practices covering the achievement of electromagnetic compatibility (EMC) and noise mitigation, as well as operators’ safety and equipment protection. The second part of the paper put great emphasis on data integrity elements of the data generated by this testbed (describing the system under healthy and faulty conditions) before it is actually used for system characterization or by diagnostics and prognostics algorithms.

Application of Bayesian Family Classifiers for Cutting Tool Inserts Health Monitoring on CNC Milling

The customized usage of tool inserts plays an imperative role in the economics of machining operations. Eventually, any in-process defects in the cutting tool lead to deterioration of complete machining activity. Such defects are untraceable by the conventional practices of condition monitoring. The characterization of such in-process tool defects needs to be addressed smartly. This would also assist the requirement of ‘self-monitoring’ in Industry 4.0. In this context, induction of supervised Machine Learning (ML) classifiers to design empirical classification models for tool condition monitoring is presented herein. The variation in faulty and fault-free tool condition is collected in terms of vibrations during the face milling process on CNC (Computer Numerically Controlled) machine tool. The statistical approach is incorporated to extract attributes and the dimensionality of the attributes is reduced using the J48 decision tree algorithm. The various conditions of tool inserts are then classified using two supervised algorithms viz. Bayes Net and Naïve Bayes from the Bayesian family.

Implementation of Faulty Sensor Detection Mechanism using Data Correlation of Multivariate Sensor Readings in Smart Agriculture

Through sensor networks, agriculture can be connected to the IoT, which allows us to create connections among agronomists, farmers, and crops regardless of their geographical differences. Faulty sensor detection is critical in IoT. When a sensor becomes faulty, missing data and/or bad data is provided to the control and management systems, which may lead to potential malfunction or even system failures. Because of this, a sensor fault detection mechanism must be implemented in an IoT system to eliminate this potential fault. This paper focuses on the implementation of a faulty sensor detection mechanism using data correlation among multivariate sensor readings, which is called Multivariate Faulty Sensor Detection Mechanism (Multi-FSDM) in a smart agriculture system. The smart agriculture system is attached with multi-variate sensors, which are moisture, temperature, and water sensor. These sensors are connected to Arduino UNO, which is equipped with an ESP8266 Wi-Fi module for internet connectivity. ThingsBoard is selected as the IoT cloud platform. The sensor readings are collected periodically and send to the cloud via the internet. Multi-FSDM calculates the correlation between each sensor reading to determine the health condition of each sensor. When all sensors are in good condition, all sensor readings are correlated with each other. However, when any sensor becomes faulty, sensor readings become uncorrelated. Once uncorrelated sensor readings occur, this means a faulty sensor is detected. Based on the findings, it is proven that Multi-FSDM can detect each sensor state on the smart agriculture system either in a good or faulty condition. When a sensor becomes faulty, Multi-FSDM detects and determines the faulty sensor successfully.

Trends and Challenges in Intelligent Condition Monitoring of Electrical Machines Using Machine Learning

A review of the fault diagnostic techniques based on machine is presented in this paper. As the world is moving towards industry 4.0 standards, the problems of limited computational power and available memory are decreasing day by day. A significant amount of data with a variety of faulty conditions of electrical machines working under different environments can be handled remotely using cloud computation. Moreover, the mathematical models of electrical machines can be utilized for the training of AI algorithms. This is true because the collection of big data is a challenging task for the industry and laboratory because of related limited resources. In this paper, some promising machine learning-based diagnostic techniques are presented in the perspective of their attributes.

Statistical residual-based time series methods for multicopter fault detection and identification

This paper presents the introduction, investigation, and critical assessment of three data-driven statistical residual-based time series methods for rotor fault detection and identification (FDI) in multicopters. A concise overview of statistical residual-based FDI methods is provided based on scalar (univariate) and vector (multivariate) stochastic time series models. The FDI methods employed in this study are based on identified response-only parametric scalar (univariate) and vector (multivariate) autoregressive (AR) representations of multicopter attitudes (time series), as the external excitation is non-observable, and their corresponding model residuals obtained under the considered healthy and faulty multicopter states. The comparative assessment of the effectiveness of three residual-based statistical FDI methods is presented in the face of external disturbances, namely three different levels of turbulence, and for different rotor fault scenarios. To the authors' best of knowledge, this is the first time that residual-based statistical time series methods are investigated and evaluated with respect to multicopter FDI. The unique characteristics of the presented methods are: (i) the data-driven stochastic identification of the multicopter dynamics under healthy and faulty rotor conditions is based only on the use of multicopter attitude signals, i.e. roll, pitch, and yaw, without the need to use additional aircraft states; (ii) there is no analytical modeling involved and the subsequent development of a stochastic multicopter FDI framework does not require knowledge of the controller effort to detect and classify rotor faults. The fault detection methods based on Vector AutoRegressive (VAR) models exhibit improved performance compared to their scalar counterparts, as indicated by lower false alarms and missed fault rates. In the case of rotor fault identification (classification), the methods that are based on scalar AR models exhibit reduced rotor fault classification accuracy, while the VAR-based methods outperform their scalar counterparts and can achieve a fault identification accuracy of up to 99.6%.

Discriminative common vector in sufficient data Case: A fault detection and classification application on photovoltaic arrays

In this study, the derivation of the Discriminative Common Vector (DCV) approach which is first introduced for a face recognition task in the insufficient data case, for the sufficient data case is obtained and it is applied for a photovoltaic (PV) panel fault detection and classification. Two experimental studies are performed including two different fault configurations. In the first experimental study, as the faulty conditions open-circuit, short-circuit, and partial shading conditions are taken and healthy condition is taken as reference. Thus, a four-class fault detection and classification scheme is constructed. In the second experimental study, the serial resistance degradation fault is considered. This fault detection and classification scheme includes four classes that are healthy and three different serial resistance degradation. The data used in the experimental studies are formed to be 1x3 dimensional vectors which include the current, voltage, and power values obtained from the simulations in the PSIM program. In all two experimental studies for each class, a discriminative common vector (DCV) which represents the common properties of that class, thus, having a high discriminative ability is obtained. As a contribution to the literature, the derivation of DCVA which has high discrimination ability for sufficient data case, and usage of it for PV panels fault detection and classification is proposed for the first time in this study. The proposed method's performance is evaluated with the performance of PCA method that is recently used for the fault detection and classification problem in PV panel systems in the literature. In the first experimental study, the proposed method's performance (99%) is obtained significantly higher than the performance of the PCA method (95%). And in the second experimental study, while PCA can only detect the faulty condition but cannot classify the serial resistance degradation, the proposed method can both detect and classify with 99% accuracy the PV panel serial resistance degradation.

Decoupling Adaptive Sliding Mode Observer Design for Wind Turbines Subject to Simultaneous Faults in Sensors and Actuators

This paper proposes an adaptive sliding mode observer (ASMO)-based approach for wind turbines subject to simultaneous faults in sensors and actuators. The proposed approach enables the simultaneous detection of actuator and sensor faults without the need for any redundant hardware components. Additionally, wind speed variations are considered as unknown disturbances, thus eliminating the need for accurate measurement or estimation. The proposed ASMO enables the accurate estimation and reconstruction of the descriptor states and disturbances. The proposed design implements the principle of separation to enable the use of the nominal controller during faulty conditions. Fault tolerance is achieved by implementing a signal correction scheme to recover the nominal behavior. The performance of the proposed approach is validated using a 4.8 MW wind turbine benchmark model subject to various faults. Monte-Carlo analysis is also carried out to further evaluate the reliability and robustness of the proposed approach in the presence of measurement errors. Simplicity, ease of implementation and the decoupling property are among the positive features of the proposed approach.

Real-time fault detection system for large scale grid integrated solar photovoltaic power plants

A new fault detection system is proposed in this study for large-scale grid-tied PV power plants. The fault detection system performs string level comparison of DC power of Actual PV Plant and a simulated PV plant, referred as Theoretical PV Plant. The comparison is performed with a statistical tool which distinguishes a faulty condition and identifies the nature of the fault. This statistical tool is used as outlier detector based on the William Gosset's (Student's) T-Test. The Theoretical PV Plant generates power in a simulation tool using inputs of irradiance and PV module temperature, both obtained from sensors at the Actual PV Plant. The string power of Actual PV Plant is also obtained in the simulation from the data logger in real-time environment. These string powers of Actual and Theoretical PV Plants are compared to find a faulty condition. A GUI is developed where the fault alarms appear on Real-time Status Monitor whenever a fault occurs in the Actual PV Plant. The proposed fault detection system has been validated on a 125 kWp grid-connected PV plant.

An intelligent grid synchronization technique for microgrid system with smooth power quality using chaotic grey wolf optimization‐random forest algorithm scheme

This manuscript proposes an intelligent grid synchronization technique for microgrid system with smooth power quality using proposed approach. The proposed approach is the consolidation of chaotic grey wolf optimization (CGWO) and random forest algorithm (RFA), hence it is called CGWO-RFA approach. The major purpose of this work is to efficiently differentiate the phase angle utility signal, monitor the phase with smooth frequency varieties, take out disruptions with harmonics, and consider the power to load uninterruptedly. In the proposed approach, the CGWO method is utilized to set the optimum control signals of the converter in offline mode depending on the power variation between the source and load side. Similarly, the limits of the proposed technique are voltage variation, frequency, and phase angle between the associated phases of the generator output and grid supply. The RFA predicts the optimal control signals depending on the accomplished dataset in the online way. The proposed CGWO-RFA method is executed in MATLAB/Simulink work site and the performance is analyzed with different existing methods, like CGWOANN, DSOGIPLL, DDSRFPLL, and DSOGIFLL. Moreover, the statistical analysis, GMPPT searching duration, and the brief comparison of synchronization scheme for explicit applications are likewise dissected and analyzed. Here, the GMPPT searching duration of the proposed technique is 0.413 seconds. The experimental outcomes demonstrate that the CGWO-RFA technique has high accuracy, high response, and robust to the faulty conditions.

Speed‐loop frequency‐adaptive and current‐loop optimal harmonic periodic controllers for fault‐tolerant SPMSM drive systems

The surface permanent magnet synchronous motor (SPMSM) drive system has been widely used in the industry due to its high power density, high efficiency and easy to control. nature The author proposes a speed-loop frequency-adaptive periodic controller and a current-loop optimal harmonic periodic controller for a fault-tolerant SPMSM drive system, including normal operating conditions and faulty operating conditions. The faulty conditions consist of an insulated gate bipolar transistor (IGBT) open-circuit and an IGBT short-circuit. A digital signal processor, TMS-320F-2808, manufactured by Texas Instruments, is used as a control centre to execute the proposed fault-detection, fault-diagnosis, frequency-adaptive and optimal harmonic periodic control algorithms. Experimental results show the proposed advanced periodic controllers can provide better performance than the proportional integral controller and the classic periodic controller, including transient responses, load disturbance responses, and tracking responses under normal and faulty conditions.

Convolutional neural network based bearing fault diagnosis of rotating machine using thermal images

The bearings are the crucial components of rotating machines in an industrial firm. Unplanned failure of these components not only increases the downtime, but also leads to production loss. This paper presents a non-invasive thermal image-based method for bearing fault diagnosis in rotating machines. Thermal images of rolling-element bearing in six conditions have been considered, including one healthy and five faulty conditions, and then a comparison based on classification performance has been done using shallow and deep learning approaches incorporating artificial neural network (ANN) and convolutional neural network (CNN). The CNN used in this work is based on the LeNet-5 structure and has proved to be a better than the ANN. It has been concluded that infrared thermography can be used in a non-contact way to automatically identify the faults that help to detect early warnings, irrespective of speeds and hence ensures reduced system shutdowns causing by bearing failure.

Identification of downhole conditions in geological drilling processes based on quantitative trends and expert rules

In drilling processes, faulty downhole conditions often lead to drilling performance degradation and even serious accidents, such as the blowout, and well collapse. To improve the drilling efficiency and enhance the process safety, a new downhole condition identification method is proposed for geological drilling processes based on quantitative trends and expert rules. A knowledge base that associates the quantitative trends and downhole conditions is established based on variational trends extracted from the historical data and rules summarized from the drilling operation manual. When the new data arrive for online monitoring, the variational trends are extracted, and then, the downhole condition is identified by comparing such trends with each rule in the knowledge base. The effectiveness and practicality of the proposed method are demonstrated by industrial case studies with real drilling process data.

A Combined Short Time Fourier Transform and Image Classification Transformer Model for Rolling Element Bearings Fault Diagnosis in Electric Motors

The most frequent faults in rotating electrical machines occur in their rolling element bearings. Thus, an effective health diagnosis mechanism of rolling element bearings is necessary from operational and economical points of view. Recently, convolutional neural networks (CNNs) have been proposed for bearing fault detection and identification. However, two major drawbacks of these models are (a) their lack of ability to capture global information about the input vector and to derive knowledge about the statistical properties of the latter and (b) the high demand for computational resources. In this paper, short time Fourier transform (STFT) is proposed as a pre-processing step to acquire time-frequency representation vibration images from raw data in variable healthy or faulty conditions. To diagnose and classify the vibration images, the image classification transformer (ICT), inspired from the transformers used for natural language processing, has been suitably adapted to work as an image classifier trained in a supervised manner and is also proposed as an alternative method to CNNs. Simulation results on a famous and well-established rolling element bearing fault detection benchmark show the effectiveness of the proposed method, which achieved 98.3% accuracy (on the test dataset) while requiring substantially fewer computational resources to be trained compared to the CNN approach.

Experimental evaluation of negative-sequence voltage compensation in distribution networks by a modular multilevel static synchronous compensator

This paper presents a negative-sequence voltage compensation strategy of a distribution network by using a static synchronous compensator based on modular multilevel converter. Mathematical relations of the static compensator are used to derive small-signal linearised models, in the synchronous reference frame, and to design voltage and current controllers to compensate for unbalanced voltages at the point of common coupling. Moreover, a comprehensive model of the DC bus voltage with a control loop implementation are presented. Furthermore, a notch filter is connected in the feedback path of the DC voltage control loop to eliminate the oscillation in the DC voltage. Digital simulations results, obtained with a 10 MVA / 24 kV MMC-DSTATCOM with 14 submodules per arm, will be used to validate the small-signal linearised mathematical models, and the performance of the designed controllers, during steady-state and faulty grid conditions. In addition experimental results obtained with a small-scale MMC prototype, with 03 submodules per arm, will be presented to demonstrate the feasibility of the compensation strategy proposed here.

Fault‐tolerant individual pitch control of floating offshore wind turbines via subspace predictive repetitive control

AbstractIndividual pitch control (IPC) is an effective and widely used strategy to mitigate blade loads in wind turbines. However, conventional IPC fails to cope with blade and actuator faults, and this situation may lead to an emergency shutdown and increased maintenance costs. In this paper, a fault‐tolerant individual pitch control (FTIPC) scheme is developed to accommodate these faults in floating offshore wind turbines (FOWTs), based on a Subspace Predictive Repetitive Control (SPRC) approach. To fulfill this goal, an online subspace identification paradigm is implemented to derive a linear approximation of the FOWT system dynamics. Then, a repetitive control law is formulated to attain load mitigation under operating conditions, both in healthy and faulty conditions. Since the excitation noise used for the online subspace identification may interfere with the nominal power generation of the wind turbine, a novel excitation technique is developed to restrict excitation at specific frequencies. Results show that significant load reductions are achieved by FTIPC, while effectively accommodating blade and actuator faults and while restricting the energy of the persistently exciting control action.

Determining threshold values of operating motor oils to diagnose internal combustion engines

Technical fluids (engine oil, antifreeze) have to meet their requirements during the standard operating life to ensure the standard service life of combustion engine systems and mechanisms. The stability of the engine oil during engine operation depends on many factors. Motor oil touches all the processes in the internal combustion engine and can serve as a source of diagnostic information, which will make it possible to carry out maintenance and repair of engine parts as needed, to increase the reliability and durability of the internal combustion engine. The results of the oil sample analysis for each indicator allow us to draw distribution density curves for the serviceable and faulty engine condition. Following the results of the analysis, it is necessary to compare the value of the index with its threshold values, separating the zone of operation condition from the zone of the engine faulty condition. Since the number of serviceable engines under operating conditions is always greater than the number of faulty ones, at the first stage of oil quality control, it is possible to determine the threshold values of indicators separating the zone of normal wear (engine serviceable condition) from the zone of increased wear. The research has resulted in an algorithm for calculating and determining the threshold values of motor oils for tractor engines operated on farms in the Omsk region. The authors selected the values based on two oil indicators: kinematic viscosity at 1000 C and flashpoint. The distribution and probability integral of these indicators are better smoothed out by the normal Gauss law. The researchers obtained the maximum and minimum values of indicators corresponding to the 5% boundary of the probability integral.

Transient Stability Enhancement of a Power System Considering Integration of FACT Controllers Through Network Structural Characteristics Theory

Modern power systems are topologically and structurally complicated due to their complex interconnections. Consequently, the complexity of the dynamic stability assessment be-comes more tedious, most especially, when considering a power electronics-based power system operating under faulty conditions. This paper, therefore suggests an alternative approach of Network Structural-Based Technique (NSBT) for the analysis and enhancement of transient stability of a power system considering Flexible Alternating Current Transmission Systems (FACTS) devices integration. The mathematical formulations based on the NSBT as well as the dynamic swing equations, required for carrying out the stability analysis, are presented. The structural characteristics of the network are captured by considering the interconnections of the network elements and the impedances between them. The eigenvalue analysis is then explored to identify suitable and possibly weak load node locations where the influence of FACTS device placement within the network, could be most beneficial. The transient stability analysis before and after critical outage conditions is investigated. The transient stability of the network operating under critical outage condition is then enhanced considering the integration of a multi- UPFC controller, which is suitably located as identified by NSBT. The effectiveness of the suggested approach is tested using the modified standard IEEE 5-bus, 30-bus networks as well as the practical Nigerian 28-bus grid incorporating a multi-FACTs controller. The results obtained show that the FACTS device contributes significantly to improving the transient stability of a multi-FACTS-based power network. The information provided by this study is highly beneficial to the system operators, utilities investors and power engineers, most especially, for predicting system collapse during critical outage conditions.

Exploitation of force displacement curves in blanking\u2014feature engineering beyond defect detection

With the current tendency of mass production towards customer-oriented serial production, blanking processes are facing new challenges. They require an increase in knowledge about faulty process conditions and their influence on the quality of a component as well as an instruction for a target-oriented adaptation of the process. The aim of this study is therefore to identify property deviations based on force-displacement curves and to establish correlations between the quality of the component and features of force-displacement curves. For this purpose, parameter variations are carried out on a high-speed press and features are extracted from these measured time series. Afterwards, the correlation between varying process parameters and features is carried out to obtain a conclusion about the condition of the component. The results of these studies for a regression analysis form the basis for a decision support system to identify deviations of the component as well as faulty process conditions. The paper shows that a reliable correlation between the quality of the component and force-displacement curves is possibly based on the feature engineering approach even under industrial boundary conditions. This also applies to the simultaneous modification and variations within a limited range of several process parameters.

Artificial Neural Network Fault Detection For Transmission Line Protection.(Dept.E)

The artificial neural network is a powerful tool for the detection of the transmission line faults due to its ability to differentiate between various patterns. In this paper, simulation of power system under normal and faulty conditions are carried out using electromagnetic transient program. The voltage and current waveforms at the relay location for normal and fault conditions are extracted. The waveforms obtained are preprocessed in order to improve the performance of the neural network used. Three neural networks are built one for fault detection, one for fault type and a third for fault location. The proposed technique is tested with different types of faults and successive decision was reached.

Transient and Protection Performance of a Fixed Series Compensated 500 kV Transmission Line During Various Types of Faulty Conditions

This paper presents a comparison of results between inserted and non-inserted series compensation technology in the network during healthy and faulty conditions. The numerous types of fault have been examined in compensated and uncompensated conditions. It was found in the literature that the transfer of power without series compensation led to increase the transient current and voltage. Therefore, a fixed series compensation scheme is adopted in normal and faulty conditions of the transmission line to solve the problem mentioned above using MATLAB/SIMULINK. Also, this paper introduces the addition of two compensated units associated with a suitable protection system in a transmission line. This technique can improve the performance of 500 kV extra high voltage transmission line and mitigate the fault current magnitude during various type of faults such as phase to ground (Ph-G), double phase to ground (2Ph-G), three phase to ground (3Ph-G). In addition, concerning the overvoltage problems across a series capacitor bank during the disturbance, the system is boosted by a protection technique associated with a suitable control system. The design is inserted into the system to protect the series capacitor bank, which in turn overcomes the severity of overvoltage on several types of faulty conditions. It also simulated and evaluated with the help of MATLAB/SIMULINK.