Different Classes Of Faults Research Articles

Incrementally Contrastive Learning of Homologous and Interclass Features for the Fault Diagnosis of Rolling Element Bearings

Bearing condition is a non-negligible part of mechanical equipment health monitoring. Most of the existing bearing fault diagnosis methods are based on the premise that all data classes are known and lack the capability of incremental diagnosis of fault modes. However, in engineering practice, the initial monitoring data only provide normal condition, and the subsequent data of different classes of faults are collected gradually. To address this practical problem, we propose incremental contrastive learning of homologous and interclass features for bearing to achieve incremental diagnosis of bearing fault modes from single to multiple classes. Important homologous and interclass features of bearings are first extracted by contrastive learning. The obtained features are then employed to establish a distance threshold for the anomaly diagnosis of subsequent samples. Upon appearing anomalies incrementally up to a certain amount, novel classes are upgraded and fed back to the model. In this way, new class data are treated as incremental learning resources. The proposed method was evaluated using both benchmark bearing and gearbox bearing experiments. Results show supreme diagnostic performance compared to peer state-of-the-art approaches. The present method is intrinsic in extracting homologous and interclass features for practical bearing fault diagnostics.

Fault simulation for design for testability inserted designs

<p>Systematic design for testability (DFT) is a technique to enhance the testability of design so that it is further organized and self-regulating. The objective of systematic DFT is to enhance a circuit's operability and evidence. This can be performed in a variety of ways. The scan pattern method is the extremely predominant, and it modifies the design's internal sequential circuitry. In this manuscript, frequently used industry standard functional register-transfer level (RTL) designs are chosen. Structured DFT approach is adopted to do scan insertion and automatic test pattern generation (ATPG) to enhance the testability. Proposed methodology provides the controllability and observability for the clocks and reset used in chosen RTL designs by eliminating S rule and D rule violations by adding test logic. Also able to insert stuck at faults and achieve fault coverage of 97.78% and test coverage of 99.26% for DFT architecture for Wallace tree multiplier design, and found different classes of faults as testable and untestable faults and also performed fault simulation for the intended designs to detect fault from the created deterministic patterns.</p>

Class Imbalanced Fault Diagnosis via Combining K-Means Clustering Algorithm with Generative Adversarial Networks

Recent advancements in machine learning and communication technologies have enabled new approaches to automated fault diagnosis and detection in industrial systems. Given wide variation in occurrence frequencies of different classes of faults, the class distribution of real-world industrial fault data is usually imbalanced. However, most prior machine learning-based classification methods do not take this imbalance into consideration, and thus tend to be biased toward recognizing the majority classes and result in poor accuracy for minority ones. To solve such problems, we propose a k-means clustering generative adversarial network (KM-GAN)-based fault diagnosis approach able to reduce imbalance in fault data and improve diagnostic accuracy for minority classes. First, we design a new k-means clustering algorithm and GAN-based oversampling method to generate diverse minority-class samples obeying the similar distribution to the original minority data. The k-means clustering algorithm is adopted to divide minority-class samples into k clusters, while a GAN is applied to learn the data distribution of the resulting clusters and generate a given number of minority-class samples as a supplement to the original dataset. Then, we construct a deep neural network (DNN) and deep belief network (DBN)-based heterogeneous ensemble model as a fault classifier to improve generalization, in which DNN and DBN models are trained separately on the resulting dataset, and then the outputs from both are averaged as the final diagnostic result. A series of comparative experiments are conducted to verify the effectiveness of our proposed method, and the experimental results show that our method can improve diagnostic accuracy for minority-class samples.

Enhancement of Mutation Testing via Fuzzy Clustering and Multi-Population Genetic Algorithm

Mutation testing, a fundamental software testing technique, which is a typical way to evaluate the adequacy of a test suite. In mutation testing, a set of mutants are generated by seeding the different classes of faults into a program under test. Test data shall be generated in the way that as many mutants can be killed as possible. Thanks to numerous tools to implement mutation testing for different languages, a huge amount of mutants are normally generated even for small-sized programs. However, a large number of mutants not only leads to a high cost of mutation testing, but also make the corresponding test data generation a non-trivial task. In this paper, we make use of intelligent technologies to improve the effectiveness and efficiency of mutation testing from two perspectives. A machine learning technique, namely fuzzy clustering, is applied to categorize mutants into different clusters. Then, a multi-population genetic algorithm via individual sharing is employed to generate test data for killing the mutants in different clusters in parallel when the problem of test data generation as an optimization one. A comprehensive framework, termed as <inline-formula><tex-math notation="LaTeX">$\mathbf {FUZGENMUT}$</tex-math></inline-formula> , is thus developed to implement the proposed techniques. The experiments based on nine programs of various sizes show that fuzzy clustering can help to reduce the cost of mutation testing effectively, and that the multi-population genetic algorithm improves the efficiency of test data generation while delivering the high mutant-killing capability. The results clearly indicate that the huge potential of using intelligent technologies to enhance the efficacy and thus the practicality of mutation testing.

Fault detection for air conditioning system using machine learning

Air conditioning system is a complex system and consumes the most energy in a building. Any fault in the system operation such as cooling tower fan faulty, compressor failure, damper stuck, etc. could lead to energy wastage and reduction in the system’s coefficient of performance (COP). Due to the complexity of the air conditioning system, detecting those faults is hard as it requires exhaustive inspections. This paper consists of two parts; i) to investigate the impact of different faults related to the air conditioning system on COP and ii) to analyse the performances of machine learning algorithms to classify those faults. Three supervised learning classifier models were developed, which were deep learning, support vector machine (SVM) and multi-layer perceptron (MLP). The performances of each classifier were investigated in terms of six different classes of faults. Results showed that different faults give different negative impacts on the COP. Also, the three supervised learning classifier models able to classify all faults for more than 94%, and MLP produced the highest accuracy and precision among all.

Online Fault Diagnosis in Industrial Processes Using Multimodel Exponential Discriminant Analysis Algorithm

Fault diagnosis is used to identify the fault cause of the online abnormality, which is crucial for efficient and optimal operation of industrial processes. Due to the time-varying characteristics of fault process, the historical fault data may consist of multiple patterns and cannot be described accurately using a single model, which may result in poor performance of conventional multivariable statistical methods. In this brief, a multimodel exponential discriminant analysis (MEDA) algorithm is proposed for solving the aforementioned fault diagnosis problem. First, the samples of each fault class are clustered into different subclasses using the fast search and find of density peaks algorithm and the proposed cluster index. Subsequently, the between- and within-subclass exponential covariance matrices are calculated based on the subclasses and then the multimodel exponential discriminant model can be developed. Finally, recursively update the cluster center and the multimodel exponential discriminant model until the developed subclasses can be well separated and better discriminant performance can be obtained. Besides, a probabilistic MEDA algorithm and its corresponding online probabilistic diagnosis are also described to develop fuzzy model, so that the fault classes whose subclasses have fuzzy boundaries can also be effectively diagnosed. The Tennessee Eastman process is used to validate the diagnosis performance of the proposed MEDA algorithm, and the experimental results illustrate that the proposed algorithm can efficiently diagnose different classes of faults.

Fault Diagnosis of Active Magnetic Bearing⁻Rotor System via Vibration Images.

As important sources in fault diagnosis of rotary machinery, vibration signals are usually processed in the time or frequency domain as features to distinguish different classes of faults. However, these kinds of processing methods always ignore the corresponding relations among multiple signals, resulting in information loss. In this paper, a new fault description strategy named vibration image is proposed, based on which three new kinds of features are extracted, containing coupling information between different channels of vibration signals. Additionally, a new feature fusion method called two-layer AdaBoost is designed to train the fault recognition model, which avoids overfitting when the dataset is not large enough. Features based on vibration images combined with two-layer AdaBoost are adopted to diagnose faults of rotary machinery. Taking an active magnetic bearing-rotor system as the experimental platform, a dataset with four classes of faults is collected and our algorithm achieves good performance. Meanwhile, features based on vibration images and two-layer AdaBoost are both proved to be efficient separately.

Methylcyclohexane Continuous Distillation Column Fault Detection Using Stationary Wavelet Transform &amp; Fuzzy C-means

It is extremely difficult to develop fault detection and diagnosis approaches for systems composed of several complex processes. This work is placed in the context of detection and diagnosis of the operating faults of an industrial installation. Indeed, the installation in this study is a Methylcyclohexane continuous column from a mixture of toluene/methylcyclohexane in which the mass composition was defined to 23% of methylcyclohexane. The studied system, allows the separation of the more volatile component which is methylcyclohexane contained in the liquid mixture. We use K-means clustering technique combined with wavelet transform for noise reduction in order to determine precisely data mapping to different classes of faults in the distillation column. This approach is compared with the exclusive use of K-means and its classification accuracy is proved. The developed technique is implemented and tested against a dataset, which covers two modes of operation of the distillation column: the normal mode, and the abnormal mode. The latter mode is represented by the four most common dysfunctions of the distillation column.

Software Product Line Testing Based on Feature Model Mutation

The Feature Model (FM) is a fundamental artifact of the Software Product Line (SPL) engineering, used to represent commonalities and variabilities, and also to derive products for testing. However, the test of all features combinations (products) is not always possible in practice. Due to the growing complexity of the applications, only a subset of products is usually selected. The selection is generally based on combinatorial testing, to test features interactions. This kind of selection does not consider different classes of faults that can be present in the FM. The application of a fault-based approach, such as mutation-based testing, can increase the probability of finding faults and the confidence that the SPL products match the requirements. Considering that, this paper introduces a mutation approach to select products for the feature testing of SPLs. The approach can be used similarly to a test criterion in the generation and assessment of test cases. It includes (i) a set of mutation operators, introduced to describe typical faults associated to the feature management and to the FM; and (ii) a testing process to apply the operators. Experimental results show the applicability of the approach. The selected test case sets are capable to reveal other kind of faults, not revealed in the pairwise testing.

Towards Semantic Mutation Testing of Aspect-Oriented Programs

Aspect-oriented programs have received much attention from software testing researchers. Various testing techniques and approaches have been proposed to tackle issues and challenges when testing aspect-oriented programs including traditional mutation testing. In traditional mutation testing of aspect-oriented programs, mutants are generated by making small changes to the syntax of the aspect-oriented language. Recently, a new approach known as semantic mutation testing has been proposed. This approach mutates the semantics of the language in which the program is written. The mutants generated misunderstandings of the language which are different classes of faults. Aspect-oriented programming presents itself with different properties that can be further explored with respect to semantic mutation testing. This paper describes various possible scenarios that semantic mutation testing strategy might have particular value in testing aspect-oriented programs.

Translationally adaptive fuzzy classifier for transformer impulse fault identification

The determination of transformer fault categories using soft-computing based techniques has been the subject of much research in the recent past. The development of an adaptive fuzzy classifier which can effectively determine various classes or categories of series and shunt impulse faults in a wide range of power transformers is described. The system employs a self-generating module to automatically derive a fuzzy rule base from predefined input and output membership functions (MFs) and a given data set for different fault classes. The accuracy of the system is further improved by translationally adapting output MF(s) either forward or backward, keeping their size and shape invariant. The database for different classes of faults is developed from FFT operation on current and voltage waveforms, obtained for different possible fault conditions simulated for given transformer models (EMTP) using an electromagnetic transients program. This database is used to create training and testing data sets required to design the fuzzy based classifier system. The usefulness of the proposed fuzzy based classifier is demonstrated on the basis of performances shown for four example power transformers of 1 MVA, 3 MVA, 5 MVA and 60 MVA ratings.

Slip patterns and earthquake populations along different classes of faults in elastic solids

Numerical simulations of slip instabilities on a vertical strike‐slip fault in an elastic half‐space are performed for various models belonging to two different categories. The first category consists of inherently discrete cellular fault models. Such are used to represent fault systems made of segments (modeled by numerical cells) that can fail independently of one another. Their quasi‐independence is assumed to provide an approximate representation of strong fault heterogeneity, due to geometric or material property disorder, that can arrest ruptures at segment boundaries. The second category consists of models having a well‐defined continuum limit. These involve a fault governed by rate‐ and state‐dependent friction and are used to evaluate what types of property heterogeneity could lead to the quasi‐independent behavior of neighboring fault segments assumed in the first category. The cases examined include models of a cellular fault subjected to various complex spatial distributions of static to kinetic strength drops, and models incorporating rate‐ and state‐dependent friction subjected to various spatial distributions of effective stress (normal stress minus pore pressure). The results indicate that gradual effective stress variations do not provide a sufficient mechanism for the generation of observed seismic response. Strong and abrupt fault heterogeneity, as envisioned in the inherently discrete category, is required for the generation of complex slip patterns and a wide spectrum of event sizes. Strong fault heterogeneity also facilitates the generation of rough rupture fronts capable of radiating high‐frequency seismic waves. The large earthquakes in both categories of models occur on a quasi‐periodic basis; the degree of periodicity increases with event size and decreases with model complexity. However, in all discrete segmented cases the models generate nonrepeating sequences of earthquakes, and the nature of the large (quasi‐periodic) events is highly variable. The results indicate that expectations for regular sequences of earthquakes and/or simple repetitive precursory slip patterns are unrealistic. The frequency‐size (FS) statistics of the small failure episodes simulated by the cellular fault models are approximately self‐similar with b ≈ 1.2 and bA ≈ 1, where b and bA are b values based on magnitude and rupture area, respectively. For failure episodes larger than a critical size, however, the simulated statistics are strongly enhanced with respect to self‐similar distributions defined by the small events. This is due to the fact that the stress concentrated at the edge of a rupture expanding in an elastic solid grows with the rupture size. When the fault properties (e.g., geometric irregularities) are characterized by a narrow range of size scales, the scaling of stress concentrations with the size of the failure zone creates a critical rupture area terminating the self‐similar earthquake statistics. In such systems, events reaching the critical size become (on the average) unstoppable, and they continue to grow to a size limited by a characteristic model dimension. When, however, the system is characterized by a broad spectrum of size scales, the above phenomena are suppressed and the range of (apparent) self‐similar FS statistics is broad and characterized by average b and bA values of about 1. The simulations indicate that power law extrapolations of low‐magnitude seismicity will often underestimate the rate of occurrence of moderate and large earthquakes. The models establish connections between features of FS statistics of earthquakes (range of self‐similar regimes, local maxima) and structural properties of faults (dominant size scales of heterogeneities, dimensions of coherent brittle zones). The results suggest that observed FS statistics can be used to obtain information on crustal thickness and fault zone structure.

The transient reactions of alternators

This paper is confined to demonstrating the existence of a characteristic of alternators provisionally named the transient impedance and to investigating the influence of this characteristic on a. The maximum and minimum currents flowing through a 12,000-kw turbo-alternator with and without external reactance coils, under various short circuit conditions. b. The maximum and minimum currents into different classes of faults from a system operating several such units in parallel. c. The maximum cross currents obtainable when paralleling a unit to the system considered in (b), and, d. The torque developed by the maximum currents of (a) and (b).