Nuisance Attribute Projection Research Articles

Early Prediction of Student’s Performance

Abstract: Performance degradation assessment (PDA) is of great significance to ensure safety and availability of mechanical equipment. As an important issue of PDA, the robustness of the trained model directly affects the assessment efficiency and restricts its application in practice. This paper proposes a robust modeling approach based on Student's t-hidden Markov model (Student's t-HMM) and nuisance attribute projection (NAP). NAP can remove nuisance attributes caused by individual differences from the feature space. Student's t-HMM utilizes the finite Student's t-mixture models (SMMs) to describe the observation emission densities associated with each hidden state, which can be more tolerant towards outliers than conventional HMMs. Based on these two techniques, the proposed method is supposed to be more robust and can assess the performance degradation process of new objects based on data of tested objects.

Numerical Model Driving Multi-Domain Information Transfer Method for Bearing Fault Diagnosis

Given the complexity of the application scenarios of rolling bearing and the severe scarcity of fault samples, a solution to the issue of fault diagnosis under varying working conditions along with the absence of fault samples is required. A numerical model-driven cross-domain fault diagnosis method targeting variable working conditions is proposed based on the cross-Domain Nuisance Attribute Projection (cDNAP). Firstly, the simulation datasets consisting of multiple fault types under variable working conditions are constructed to solve the problem of incomplete fault samples. Secondly, the simulation datasets are expanded by means of generating adversarial network to ensure sufficient samples for subsequent model training. Finally, cDNAP is used to obtain the cross-domain simulation projection matrix, which eliminates the variance in the distribution of measured and simulated sample features under varying working conditions. The experimental results of cross-domain for variable working conditions show that the diagnostic accuracy reaches up to 99%. Compared with DANN, DSAN, and DAAN domain adversarial neural networks, the proposed method performs better in bearing fault diagnosis.

A novel vibro-acoustic fault diagnosis method of rolling bearings via entropy-weighted nuisance attribute projection and orthogonal locality preserving projections under various operating conditions

Accurate fault pattern recognition under various operating conditions is a huge challenge for vibro-acoustic fault diagnosis of rolling bearings. Traditional feature fusion methods are difficult to extract sensitive features related to faults under various operating conditions. To solve the problem, a novel feature fusion method is proposed in this paper based on entropy-weighted nuisance attribute projection (EWNAP) and orthogonal locality preserving projections (OLPP). Specifically, the method mainly includes three steps: feature extraction, alleviating interference of operating condition, and fusion feature. First, features are extracted from the acquired sound signals. Second, by introducing the covariance matrix of the acquired signals and fuzzy entropy to improve the weighted matrix of nuisance attribute projection (NAP), the EWNAP is proposed to reduce the impact of operating conditions in these extracted features. In the end, OLPP is adopted to fuse features and obtain sensitive features. The clustering performance of the proposed method is quantitatively described by an evaluation index, and for fault pattern recognition, the vectors as samples, which are composed of features extracted via EWNAP-OLPP, are fed into the back propagation (BP) neural network. The analysis on a fault case of rolling bearings shows that the proposed method is robust for vibro-acoustic fault diagnosis of rolling bearings under various operating conditions and superior to traditional methods.

A novel multivariate signal processing-based fault diagnosis approach of rotating machinery under various operating conditions

Compared with signals collected by the single sensor, the collected multivariate signals contain more information to reflect the state of mechanical equipment, which has a positive effect on fault diagnosis. However, different acquisition channels and various operating conditions interfere with the extraction of fault features of rotating machinery. To solve this problem, taking rolling bearings as an example in this paper, a novel method is adopted to alleviate these interferences and combined with an improved extreme learning machine (ELM) to achieve intelligent fault diagnosis of rolling bearings under various operating conditions. First, adaptive projection intrinsically transformed multivariate empirical mode decomposition is used to decompose multivariate signals and obtain intrinsic mode functions of each channel to construct feature matrices. Then, nuisance attribute projection (NAP) is employed to alleviate the interference components in the feature matrix, which are originated from different channels and operating conditions. Finally, vectors belonging to the processed feature matrix as samples are input into the proposed weighted extreme learning machine (WELM) for intelligent fault classification. The weighted matrix of the WELM can compress the dimension of the sample and extract sensitive features, and the effectiveness of the proposed fault diagnosis model via the above methods is verified by experiments. Furthermore, comparative experiments show that the proposed fault diagnosis model has higher accuracy than the model combined with NAP and traditional single-hidden layer feedforward neural network or ELM. Therefore, the proposed fault diagnosis model may potentially aid experts on fault diagnosis of rotating machinery under various operating conditions.

Robust fault diagnosis of rolling bearings via entropy-weighted nuisance attribute projection and neural network under various operating conditions

Rolling bearings are crucial components in the fields of mechanical, civil, and aerospace engineering. They sometimes work under various operating conditions, which makes it harder to distinguish faults from normal signals. Nuisance attribute projection (NAP) is a technique that has been widely used in audio and image recognition to eliminate interference information in the extracted feature space. In constructing the weighted matrix of NAP, the setting of the weighted value represents the degree of interference between the feature vectors. The interference is either taken into consideration in whole, or not considered at all, which will inevitably lead to information loss. In our work, an entropy-weighted NAP (EWNAP) is proposed to deal with such “bipolar problem” in constructing the weighted matrix. The eigenvalues of covariance matrix of collected signals contain dynamical information, and the fuzzy entropy is adopted to evaluate the dispersion degree of these eigenvalues. After normalization, these entropy values are used to express the weight relationship in the weighted matrix of EWNAP. The features processed by EWNAP can be used as samples and combined with neural network to achieve fault diagnosis of rolling bearings. Furthermore, a fault diagnosis approach with insufficient data is demonstrated to validate the effectiveness of the proposed scheme. In the case studies, Case Western Reserve University bearing database and data collected from the bearing fault simulation bench are used. These case studies show that the proposed EWNAP alleviates the interference caused by various operating conditions, and the comparative analysis confirms that the proposed method works better than the conventional methods.

A new strategy to eliminate interference of varying operating conditions during multivariate signal processing-based fault diagnosis approach

Abstract Multivariate signal acquisition and processing of faulty mechanical components extract more fault characteristic information, contributing to comprehensive and accurate fault diagnosis. Multivariate empirical mode decomposition (MEMD) is an effective approach in the field of multivariate signal processing. While nuisance attribute projection (NAP) can be used to filter out the components of nuisance attributes caused by varying operating condition. This paper proposes a new strategy for eliminating interference during multivariate signal processing- based fault diagnosis approach. MEMD is used to decompose multivariate signal of faulty rolling bearing into multivariate IMFs depicting dynamical properties, with extracting quantitative features of multivariate IMFs. Then, NAP is used to eliminate nuisance attributes of varying operating conditions in the constructed feature matrices. To illustrate the effectiveness and superiority of the proposed new strategy, the extracted features are presented by t-distribution stochastic neighbour embedding (t-SNE). The dimensionalities of feature vectors are reduced to 3 on account of the visualization simplicity. The comparison analysis during application researches can validate the superiority of the proposed novel strategy.

Scalable fault models for diagnosis in a synchronous generator using feature mapping and transformation techniques

Condition based maintenance (CBM) needs data acquired during healthy and faulty conditions to develop intelligent system for fault diagnosis. However, fault injection is not allowed/possible in a highly expensive components of complex/critical systems to collect fault condition data. Therefore, proto-type/small working models are used to conduct experiments for abnormal/fault conditions, to obtain and scale the intelligence of the system for effective health monitoring of complex system. This methodology is referred as scalable fault models. For proof of concept, in this work, we considered two different capacity synchronous generators with rating of 3 kVA and 5 kVA to emulate the behavior of prototype/small working model and complex system respectively, for scalable fault models. We explored feature mapping and transformation techniques to achieve effective scalability.From the preliminary experiments, it is observed that the baseline system performance deteriorated due to the changes in the system (capacity) and its characteristics with load changes.We therefore, expressed the input features in terms of load and system independent manner, to make the features less dependent on load and system variations. We explored localityconstrained linear coding (LLC) to express the features load/system independently. It is observed that experimenting LLC with the backend support vector machine (SVM) classifier gave the best fault classification performance for linear kernel, suggesting that the faults are linearly separable in the new feature space.Since the LLC mapped feature space is linearly separable, we then explored linear feature transformation technique, nuisance attribute projection (NAP) on the LLC mapped feature space to further minimize the load/system specific variations. We observed that LLC-NAP improved the overall accuracy and sensitivity of the classifier significantly. We also noted that the performance of NAP was limited in the original feature space since the feature space (NAP without LLC) is nonlinear with load/system variations.

System Independent Fault Diagnosis for Synchronous Generator

Creating a unified fault diagnosis model that can detect faults across systems with different ratings (system independent fault diagnosis) would be of great interest in making condition-based maintenance (CBM) more popular. In this work, three phase synchronous generators with 3 and 5 kVA ratings are used for detecting stator inter-turn short circuit faults.Our baseline is a 3 kVA generator working at 1 A load during training and testing, to emulate the system/load dependent fault diagnosis. We obtained a classification accuracy of 99.75%, 100% and 100% for R phase, Y phase and B phase faults respectively. Subsequently, we evaluated the system for its load independent performance. Performance accuracy deteriorated due to the load specific variations (LSV) in the input feature vector (IFV). LSV is undesired, and we used nuisance attribute projection (NAP) to remove them. Using NAP, we obtained a performance improvement of 23.13%, 17.75% and 20.72% for three fault models on the 3 kVA generator and similar performance improvement was obtained for 5 kVA generator also.Further, we experimented for load and system independent fault diagnosis. In this case, we consider LSV and system specific variations (SSV) on IFV as undesired. We experimented with two types of NAP, (1) single step NAP, (2) stacked NAP. Experimental results show that the two staged stacked NAP outperforms. We obtained an improvement of 23.99%, 16.06% and 28.39%, in classification accuracy for three fault models, resulting in overall classification accuracy of 89.22%, 94.67% and 94.59% for R phase, Y phase and B phase fault models respectively.

Speaker age and gender classification using GMM supervector and NAP channel compensation method

One of the most important factors affecting the performance of speech-based recognition systems is the differences between training and test conditions. The Nuisance attribute projection (NAP) is an effective method for eliminating these differences, called channel effects. In this study, the effects of the NAP approach in determining age and gender groups are investigated. Mel-frequency cepstral coefficients and delta coefficients are used as a feature and Gaussian mixture models (GMM) adapted from the universal background model by maximum-a-posteriori method are used for the modeling of age and gender classes. After the GMMs corresponding to each speech are converted into mean supervectors, they are applied to a Support Vector Machine (SVM), and speeches are classified according to the age and gender group of the speakers. While linear GMM kernel based on Kullback–Leibler divergence is used instead of standard SVM kernels, the NAP channel subspace size is changed between 20 and 200 and the number of GMM components is changed between 32 and 512 to determine the optimum values for these parameters. In the tests on the aGender database, the optimum number of components is determined as 128, and the optimum NAP channel subspace size is determined as 45. The age and gender classification accuracy of the system, which is developed using these optimum parameters, is increased from 60.52 to 62.03% with the use of NAP. In addition, age classification accuracy is increased from 60.23 to 61.82% and gender classification accuracy is increased from 91.71 to 92.30%.

A Robust Performance Degradation Modeling Approach Based on Student’s t-HMM and Nuisance Attribute Projection

Performance degradation assessment (PDA) is of great significance to ensure safety and availability of mechanical equipment. As an important issue of PDA, the robustness of the trained model directly affects the assessment efficiency and restricts its application in practice. This paper proposes a robust modeling approach based on Student’s t-hidden Markov model (Student’s t-HMM) and nuisance attribute projection (NAP). NAP can remove nuisance attributes caused by individual differences from the feature space. Student’s t-HMM utilizes the finite Student’s t-mixture models (SMMs) to describe the observation emission densities associated with each hidden state, which can be more tolerant towards outliers than conventional HMMs. Based on these two techniques, the proposed method is supposed to be more robust and can assess the performance degradation process of new objects based on data of tested objects. The superiority of the proposed approach is evaluated using the vibration data from the accelerated life tests of bearings and the public XJTU-SY Bearing Datasets. The results demonstrate the robustness and effectiveness of the proposed approach for PDA modeling of rolling element bearings.

A Fault Diagnosis Approach for Rolling Bearing Based on Convolutional Neural Network and Nuisance Attribute Projection under Various Speed Conditions

Intelligent fault diagnosis is a promising tool for processing mechanical big data. It can quickly and efficiently process the collected signals and provide accurate diagnosis results. However, rotating machinery often works under various speed conditions, which makes it difficult to extract fault features. Inspired by speech recognition, the nuisance attribute projection method in speech recognition is introduced into fault diagnosis to solve the problem of feature extraction in variable speed signals. Based on the idea of unsupervised feature learning, the loss function of nuisance attribute projection is added to the loss function of convolutional neural network (CNN) to learn fault features from original data. Health status is classified according to the learned characteristics and projection matrix P. A special designed bearing dataset is employed to verify the effectiveness of the proposed method. The results show that the proposed method has a higher accuracy and a simpler framework, which is superior to the existing methods in bearing fault diagnosis.

Rolling bearing fault diagnosis and performance degradation assessment under variable operation conditions based on nuisance attribute projection

Abstract The operation conditions are always non-stationary in the operation of rotating machinery. It is the key to realize the fault diagnosis of rotating machinery under different operation conditions by extracting the features which are irrelevant to the operation conditions and contain fault information. Nuisance attribute projection (NAP) is compensation technique to eliminate the influence of interference information in the feature space which has been used in speaker recognition and face recognition. In this paper, the rolling bearing vibration signals under different operation conditions are used to verify the nuisance removing ability of (NAP) in the feature space. Above all, after NAP are applied to the simulation and measured signals under different rotating speeds and loads, the comparisons between the original features and NAP features have shown that NAP can effectively eliminate the effect of nuisance attributes through projection. Moreover, it is verified that the information of fault pattern and fault degree are retained in the features after projection by analyzing the measured signals of different fault pattern and simulation signals of different fault degree under various rotating speeds, respectively. Furthermore, it is confirmed that the NAP can get rid of the nuisance attributes by analyzing twelve bearing tests of whole life under different operation conditions and channels. On the other hand, a feature selection method based on ranking mutual information (RMI) is used in this paper to select the features of more monotonous in bearing performance degradation assessment. The application sequences of RMI and NAP are studied for their influence on the bearing performance degradation index in the last part since the different sequence may affect the assessment results. The comparison results have shown that NAP should be used before feature selection in rotating machinery fault diagnosis.

Online signature verification using i‐vector representation

Signature verification (SV) is one of the common methods for identity verification in banking, where for security reasons, it is very important to have an accurate method for automatic SV (ASV). ASV is usually addressed by comparing the test signature with the enrolment signature(s) signed by the individual whose identity is claimed in two manners: online and offline. In this study, a new method based on the i-vector is proposed for online SV. In the proposed method, a fixed-length vector, called i-vector, is extracted from each signature and then this vector is used for template making. Several techniques such as nuisance attribute projection (NAP) and within-class covariance normalisation (WCCN) are also investigated in order to reduce the intra-class variation in the i-vector space. In the scoring and decision making stage, they also propose to apply a 2-class support vector machine method. Experimental results show the proposed method could achieve 8.75% equal error rate (EER) on SigWiComp2013 database in the best case. On SVC2004 database, it also achieved 5% EER that means 11% relative improvement compared with the best reported result. In addition to its considerable accuracy gain, it has shown significant improvement in the computational cost over conventional dynamic time warping method.

An intelligent performance degradation assessment method for bearings

Bearings are one of the most frequently used components in the rotatory machinery, so the performance degradation assessment of bearings plays an important role in the prognostics and health management of systems. Hidden Markov model (HMM) is a widely applied data-driven model used for bearing performance degradation assessment and has many successful applications. A normal HMM needs to be trained in advance, which has close relationship with the evaluation system. However, the trained HMM is quite influenced by many issues, such as the data integrity and the feature space. In this paper, an intelligent bearing performance degradation assessment method based on HMM and nuisance attribute projection (NAP) is proposed. The proposed method can combine the information from the experimental data and the real-time data effectively and assess the performance since the beginning of the monitoring. The effectiveness of the proposed method is verified through an accelerated life test of rolling element bearings.

Domain Mismatch Compensation for Speaker Recognition Using a Library of Whiteners

The development of the i-vector framework for generating low dimensional representations of speech utterances has led to considerable improvements in speaker recognition performance. Although these gains have been achieved in periodic National Institute of Standards and Technology (NIST) evaluations, the problem of domain mismatch, where the system development data and the application data are collected from different sources, remains a challenging one. The impact of domain mismatch was a focus of the Johns Hopkins University (JHU) 2013 speaker recognition workshop, where a domain adaptation challenge (DAC13) corpus was created to address this problem. This paper proposes an approach to domain mismatch compensation for applications where in-domain development data is assumed to be unavailable. The method is based on a generalization of data whitening used in association with i-vector length normalization and utilizes a library of whitening transforms trained at system development time using strictly out-of-domain data. The approach is evaluated on the 2013 domain adaptation challenge task and is shown to compare favorably to in-domain conventional whitening and to nuisance attribute projection (NAP) inter-dataset variability compensation.

Hidden Markov model and nuisance attribute projection based bearing performance degradation assessment

Hidden Markov model (HMM) has been widely applied in bearing performance degradation assessment. As a machine learning-based model, its accuracy, subsequently, is dependent on the sensitivity of the features used to estimate the degradation performance of bearings. It׳s a big challenge to extract effective features which are not influenced by other qualities or attributes uncorrelated with the bearing degradation condition. In this paper, a bearing performance degradation assessment method based on HMM and nuisance attribute projection (NAP) is proposed. NAP can filter out the effect of nuisance attributes in feature space through projection. The new feature space projected by NAP is more sensitive to bearing health changes and barely influenced by other interferences occurring in operation condition. To verify the effectiveness of the proposed method, two different experimental databases are utilized. The results show that the combination of HMM and NAP can effectively improve the accuracy and robustness of the bearing performance degradation assessment system.

Intelligent fault diagnosis of synchronous generators

Condition based maintenance (CBM) requires continuous monitoring of mechanical/electrical signals and various operating conditions of the machine to provide maintenance decisions. However, for expensive complex systems (e.g. aerospace), inducing faults and capturing the intelligence about the system is not possible. This necessitates to have a small working model (SWM) to learn about faults and capture the intelligence about the system, and then scale up the fault models to monitor the condition of the complex/prototype system, without ever injecting faults in the prototype system. We refer to this approach as scalable fault models.We check the effectiveness of the proposed approach using a 3 kVA synchronous generator as SWM and a 5 kVA synchronous generator as the prototype system. In this work, we identify and remove the system-dependent features using a nuisance attribute projection (NAP) algorithm to model a system-independent feature space to make the features robust across the two different capacity synchronous generators. The frequency domain statistical features are extracted from the current signals of the synchronous generators. Classification and regression tree (CART) is used as a back-end classifier. NAP improves the performance of the baseline system by 2.05%, 5.94%, and 9.55% for the R, Y, and B phase faults respectively.

Relevance factor of maximum a posteriori adaptation for GMM–NAP–SVM in speaker and language recognition

This paper studies the relevance factor in maximum a posteriori (MAP) adaptation of Gaussian mixture model (GMM) for speaker and language recognition. Knowing that relevance factor determines how much the observed training data influence the model adaptation, thus the resulting GMM model, it is believed that more effective modeling can be achieved if the relevance factor is adaptive to the corresponding data. We therefore provide a mathematic derivation for the estimation of relevance factor. GMM supervector support vector machine (SVM) with nuisance attribute projection (NAP) (GMM–NAP–SVM) has been reported to be effective and reliable for speaker and language recognition. Being a discriminative classifier in nature, a GMM–NAP–SVM system is sensitive to the magnitude and direction of a supervector in the high dimensional space. However, when characterizing a speech utterance with GMM supervector estimated through MAP, we observe that the resulting supervector is undesirably affected by the varying duration of the utterance. We propose an adaptive relevance factor that adapts to the duration to mitigate the variability effect due to the length of utterance. We give a systematic investigation on different types of relevance factor of MAP in different applicatively platforms. We show the efficacy of the data-dependent as well as adaptive relevance factors on the National Institute of Standards and Technology (NIST) speaker recognition evaluation (SRE) 2008 and language recognition evaluation (LRE) 2009 and 2011 tasks respectively.

Improved nuisance attribute projection for face recognition

Th e illumination variation is one of the well-known problems in face recognition under uncontrolled environments. Several techniques have been presented in the literature to cope up with this problem. Lately, a technique known as Nuisance Attribute Projection (NAP), originally developed for the speaker recognition field was introduced to image processing in order to compensate for luminance artifacts. This paper extends and improves the earlier work by exploring efficient methodologies for using NAP for face recognition under varied illumination conditions. In particular, we propose a modified NAP formulation and show that NAP training can be simplified for face recognition. Additionally, we suggested a compact framework merging between NAP compensation and eigenface recognition. A series of experiments using the extended YaleB database, and a cross-validation using the PIE CMU and the Oulo databases are performed to validate our proposals.

Factor analysis method for text-independent speaker identification

Factor analysis method offers state-of-the-art performance in speaker identification during the paper. The compact representations of speakers named i-vectors are extracted from the utterances in a new low dimensional speaker- and channel-dependent space, referred to a total variability space. LBG algorithm is combined with fuzzy theory in the initialization of speaker models，which helps improve the recognition rate of the system. Channel compensation techniques, such as Linear Discriminate Analysis (LDA), Principal Component Analysis (PCA), Nuisance Attribute Projection (NAP) and Within-class Covariance Normalization (WCCN) are compared during the experiment. It can be seen that LDA followed by WCCN achieves satisfying performance. In addition, experiments contrast several identification methods. One is through Support-Vector-Machine (SVM), another one directly uses the cosine distance similarity (CDS) as the final decision score, logarithmic likelihood and vector quantization are used to compare to above two methods. It demonstrates that CDS combined with score normalization obtains better result. The testing of mobile phone database shows the robustness of the system in complex channel environment. The graphical user interface of training and testing module is simulated on MATLAB in the end of the paper.