Raw Current Signals Research Articles

Nanopore strand-specific mismatch enables de novo detection of bacterial DNA modifications.

DNA modifications in bacteria present diverse types and distributions, playing crucial functional roles. Current methods for detecting bacterial DNA modifications via nanopore sequencing typically involve comparing raw current signals to a methylation-free control. In this study, we found that bacterial DNA modification induces errors in nanopore reads. And these errors are found only in one strand but not the other, showing a strand-specific bias. Leveraging this discovery, we developed Hammerhead, a pioneering pipeline designed for de novo methylation discovery that circumvents the necessity of raw signal inference and a methylation-free control. The majority (14 out of 16) of the identified motifs can be validated by raw signal comparison methods or by identifying corresponding methyltransferases in bacteria. Additionally, we included a novel polishing strategy employing duplex reads to correct modification-induced errors in bacterial genome assemblies, achieving a reduction of over 85% in such errors. In summary, Hammerhead enables users to effectively locate bacterial DNA methylation sites from nanopore FASTQ/FASTA reads, thus holds promise as a routine pipeline for a wide range of nanopore sequencing applications, such as genome assembly, metagenomic binning, decontaminating eukaryotic genome assembly, and functional analysis for DNA modifications.

RNA m6A detection using raw current signals and basecalling errors from Nanopore direct RNA sequencing reads.

Nanopore direct RNA sequencing (DRS) enables the detection of RNA N6-methyladenosine (m6A) without extra laboratory techniques. A number of supervised or comparative approaches have been developed to identify m6A from Nanopore DRS reads. However, existing methods typically utilize either statistical features of the current signals or basecalling-error features, ignoring the richer information of the raw signals of DRS reads. Here, we propose RedNano, a deep-learning method designed to detect m6A from Nanopore DRS reads by utilizing both raw signals and basecalling errors. RedNano processes the raw-signal feature and basecalling-error feature through residual networks. We validated the effectiveness of RedNano using synthesized, Arabidopsis, and human DRS data. The results demonstrate that RedNano surpasses existing methods by achieving higher area under the ROC curve (AUC) and area under the precision-recall curve (AUPRs) in all three datasets. Furthermore, RedNano performs better in cross-species validation, demonstrating its robustness. Additionally, when detecting m6A from an independent dataset of Populus trichocarpa, RedNano achieves the highest AUC and AUPR, which are 3.8%-9.9% and 5.5%-13.8% higher than other methods, respectively. The source code of RedNano is freely available at https://github.com/Derryxu/RedNano.

Integration of wavelet packet transform, residual convolution neural network, and support vector machine for series arc fault detection

Series arc fault (SAF) poses a great challenge to the safe and stable operation of civil low-voltage distribution systems. For the accurate and rapid detection of SAF, this article proposes an SAF detection method using wavelet packet transform (WPT), residual convolution neural network (RCNN), and support vector machine (SVM). First, the raw current signal is decomposed into four wavelet components based on WPT. Then, the 1-D wavelet components are converted into 2-D matrices. Afterward, the matrices are input into RCNN through different channels. Finally, the detection results can be yielded by SVM. The effectiveness of the proposed method is verified based on offline experiments. The average detection accuracy of the proposed method is 99.72%, which is higher than that of the eight comparison methods. Moreover, the results of online experiments indicate that the detection time of the proposed method is less than 100 ms and can satisfy the requirement of standard 1699.

Bearing fault diagnosis based on a multiple-constraint modal-invariant graph convolutional fusion network

Multisensor data fusion method can improve the accuracy of bearing fault diagnosis, in order to address the problems of single-sensor data types and the insufficient exploration of redundancy and complementarity between different modal data in most existing multisensor data fusion methods for bearing fault diagnosis, a bearing fault diagnosis method based on a Multiple-Constraint Modal-Invariant Graph Convolutional Fusion Network (MCMI-GCFN) is proposed in this paper. Firstly, a Convolutional Autoencoder (CAE) and Squeeze-and-Excitation Block (SE block) are used to extract features of raw current and vibration signals. Secondly, the model introduces source domain classifiers and domain discriminators to capture modal invariance between different modal data based on domain adversarial training, making use of the redundancy and complementarity between multimodal data. Then, the spatial aggregation property of Graph Convolutional Neural Networks (GCN) is utilized to capture the dependency relationship between current and vibration modes with similar time step features for accurately fusing contextual semantic information. Finally, the validation is conducted on the public bearing damage current and vibration dataset from Paderborn University. The experimental results showed that the delivered fusion method achieved a bearing fault diagnosis accuracy of 99.6 %, which was about 9 %–11.4 % better than that with nonfusion methods.

Streamlining remote nanopore data access with slow5curl.

As adoption of nanopore sequencing technology continues to advance, the need to maintain large volumes of raw current signal data for reanalysis with updated algorithms is a growing challenge. Here we introduce slow5curl, a software package designed to streamline nanopore data sharing, accessibility, and reanalysis. Slow5curl allows a user to fetch a specified read or group of reads from a raw nanopore dataset stored on a remote server, such as a public data repository, without downloading the entire file. Slow5curl uses an index to quickly fetch specific reads from a large dataset in SLOW5/BLOW5 format and highly parallelized data access requests to maximize download speeds. Using all public nanopore data from the Human Pangenome Reference Consortium (>22 TB), we demonstrate how slow5curl can be used to quickly fetch and reanalyze raw signal reads corresponding to a set of target genes from each individual in large cohort dataset (n = 91), minimizing the time, egress costs, and local storage requirements for their reanalysis. We provide slow5curl as a free, open-source package that will reduce frictions in data sharing for the nanopore community: https://github.com/BonsonW/slow5curl.

Self-adaptive micro-hole breakout detection in the electrochemical discharge drilling process based on CNN-BiLSTM

Electrochemical discharge machining (ECDM) is an effective and promising technology for the micro-hole drilling of hard and brittle insulating materials such as glass, quartz and ceramics. Hole exit quality is an important part of through-hole machining quality in ECDM. The hole exit quality is influenced by two different machining states before and after the hole breakout. Therefore, it is necessary to identify hole breakout occurrence to provide a basis for achieving a machining strategy that matches the changing machining state and thus improves the hole exit quality. However, currently, there is no effective method to detect the hole breakout in the ECDM of micro-holes. In this paper, a self-adaptive micro-hole breakout detection method based on CNN- BiLSTM was proposed. The hole breakout detection can be expressed as a binary classification problem according to the analysis of the current signals collected before and after the hole breakout. The sufficiency of the raw current signal information was discussed. A CNN-BiLSTM model was established to detect hole breakout using the current signals as the training dataset. The CNN-BiLSTM model showed better performance compared to CNN, LSTM, BiLSTM and CNN-LSTM by comprehensive considering of accuracy, F1 score, AUC value, training time, predict time, breakout detection results and Dunn test results. Furthermore, the length of current signals used for each single detection and the threshold value used for breakout detection were discussed. An optimal threshold value was calculated, and the delay of detection was within 66 ms. The proposed method was successfully applied to the hole breakout detection in the through-hole drilling experiments and the success rate was 100 %. The hole exit area just after breakout were measured and compared to the hole exit area after hole completion, the average ratios of the former to the latter were 11.69 %, 27.29 %, 38.43 % and 44.41 % for the voltage of 39 V, 41 V, 43 V and 45 V respectively.

Differential-Augmented Current Feature Learning Network With Multi-Information Interaction for Fault Diagnosis in Electromechanical Drive System

Current-based fault diagnosis has become a promising solution for electromechanical systems due to the low cost and easy access. However, most of the existing studies require additional signal processing or diagnostic expertise to pre-process the signals due to the effects of the fundamental component and electrical noise. It is challenging to extract effective fault-related features from the raw current signals. To this end, this paper proposes a differential-augmented current feature learning network named CurrentNet for drive system fault diagnosis, which is an end-to-end model. Firstly, a differential-augmented strategy based on the raw current signal is introduced to generate complementary current representations. Furthermore, a multi-information interaction module (MIIM) is designed to adaptively capture complementary shared information between the original and enhanced signals through a parallel mechanism. Also, efficient channel attention is used to reduce the complexity of the model. Our proposed method is experimentally evaluated on two datasets and presents obvious superiority over existing fault diagnosis methods.

Accelerated nanopore basecalling with SLOW5 data format.

Nanopore sequencing is emerging as a key pillar in the genomic technology landscape but computational constraints limiting its scalability remain to be overcome. The translation of raw current signal data into DNA or RNA sequence reads, known as 'basecalling', is a major friction in any nanopore sequencing workflow. Here, we exploit the advantages of the recently developed signal data format 'SLOW5' to streamline and accelerate nanopore basecalling on high-performance computing (HPC) and cloud environments. SLOW5 permits highly efficient sequential data access, eliminating a potential analysis bottleneck. To take advantage of this, we introduce Buttery-eel, an open-source wrapper for Oxford Nanopore's Guppy basecaller that enables SLOW5 data access, resulting in performance improvements that are essential for scalable, affordable basecalling. Buttery-eel is available at https://github.com/Psy-Fer/buttery-eel.

RNA Modification Detection Using Nanopore Direct RNA Sequencing and nanoDoc2.

RNA modifications regulate multiple aspects of cellular function including RNA splicing, translation, export, decay, stability, and phase separation. One of the comprehensive ways to detect such modifications is by the recent advancement of direct RNA sequencing from Oxford Nanopore Technologies (ONT). However, this method obtains a large amount of data with high complexity in the form of raw current signal that poses a new informatics challenge to accurately detect those modifications. Here, we provide nanoDoc2, a software to detect multiple types of RNA modification from nanopore direct RNA sequencing data. The nanoDoc2 includes a novel signal segmentation algorithm based on the trace value-a base probability feature that is added by the Guppy basecalling program from ONT during processing of the raw signal. The core of nanoDoc2 includes a machine learning algorithm in which a 6-mer segmented raw current signal is analyzed by deep one-class classification using a WaveNet-based neural network. As an output, an RNA modification is detected by a statistical score in each candidate position. Herein, we describe the detailed instructions on how to use nanoDoc2 for signal segmentation, train/test the neural network, and finally predict RNA modifications present in nanopore direct RNA sequencing data.

Detection of m6A from direct RNA sequencing using a multiple instance learning framework

RNA modifications such as m6A methylation form an additional layer of complexity in the transcriptome. Nanopore direct RNA sequencing can capture this information in the raw current signal for each RNA molecule, enabling the detection of RNA modifications using supervised machine learning. However, experimental approaches provide only site-level training data, whereas the modification status for each single RNA molecule is missing. Here we present m6Anet, a neural-network-based method that leverages the multiple instance learning framework to specifically handle missing read-level modification labels in site-level training data. m6Anet outperforms existing computational methods, shows similar accuracy as experimental approaches, and generalizes with high accuracy to different cell lines and species without retraining model parameters. In addition, we demonstrate that m6Anet captures the underlying read-level stoichiometry, which can be used to approximate differences in modification rates. Overall, m6Anet offers a tool to capture the transcriptome-wide identification and quantification of m6A from a single run of direct RNA sequencing.

A novel current sensor indicator enabled WAFTR model for tool wear prediction under variable operating conditions

The health indicators (HIs) were extracted from the current sensor to represent the tool wear progression. The extracted HIs were found poorly correlated with the progression of tool wear as the raw current sensor signal was susceptible to the influence of other parts and structures in the machine tool. Hence, this paper proposed a novel current sensor-based HI that utilized the mean of inverse hyperbolic cosine function fitted to an envelope of the current signal to improve the correlation. Using the extracted HIs, many bespoke machine learning (ML) models have been developed by researchers. However, these models have many hyperparameters, difficult to interpret and especially poor prediction accuracy has been observed under variable operating conditions. This study overcame these issues by proposing a Weibull Accelerated Failure Time Regression (WAFTR) model, which combines process parameters data with HI for improving the prediction accuracy under variable operating conditions. This model mapped a functional relationship with tool wear in the form of probability density function to identify best HIs and acceleration/deacceleration factors which makes it interpretable. The acceleration/deacceleration factors are useful to deaccelerate the tool wear evolution by controlling the specific values of the machining parameters.

Expanding the Molecular Alphabet of DNA-Based Data Storage Systems with Neural Network Nanopore Readout Processing.

DNA is a promising next-generation data storage medium, but challenges remain with synthesis costs and recording latency. Here, we describe a prototype of a DNA data storage system that uses an extended molecular alphabet combining natural and chemically modified nucleotides. Our results show that MspA nanopores can discriminate different combinations and ordered sequences of natural and chemically modified nucleotides in custom-designed oligomers. We further demonstrate single-molecule sequencing of the extended alphabet using a neural network architecture that classifies raw current signals generated by Oxford Nanopore sequencers with an average accuracy exceeding 60% (39× larger than random guessing). Molecular dynamics simulations show that the majority of modified nucleotides lead to only minor perturbations of the DNA double helix. Overall, the extended molecular alphabet may potentially offer a nearly 2-fold increase in storage density and potentially the same order of reduction in the recording latency, thereby enabling new implementations of molecular recorders.

Bearing Fault Detection for Doubly fed Induction Generator Based on Stator Current

Bearing failure often occurs in a doubly fed induction generator. The fault diagnosis method based on the current signals has been attracted much attention. In this article, we propose different discrete digital models and their measure functions employing random theory. First, based on the raw current signals with the probability density function (PDF), a distributed discrete digital model is proposed; to avoid finding the PDF in the raw current signals, a discrete digital model of the moment feature and a discrete digital model of raw data are proposed. Then, six measurement functions are proposed as features of the discrete digital model for pattern recognition and condition monitoring of bearing. Finally, the effectiveness of the current method is demonstrated by comparing different signal processing methods.

An End-to-End, Real-Time Solution for Condition Monitoring of Wind Turbine Generators

Data-driven wind generator condition monitoring systems largely rely on multi-stage processing involving feature selection and extraction followed by supervised learning. These stages require expert analysis, are potentially error-prone and do not generalize well between applications. In this paper, we introduce a collection of end-to-end Convolutional Neural Networks for advanced condition monitoring of wind turbine generators. End-to-end models have the benefit of utilizing raw, unstructured signals to make predictions about the parameters of interest. This feature makes it easier to scale an existing collection of models to new predictive tasks (e.g., new failure types) since feature extracting steps are not required. These automated models achieve low Mean Squared Errors in predicting the generator operational state (40.85 for Speed and 0.0018 for Load) and high accuracy in diagnosing rotor demagnetization failures (99.67%) by utilizing only raw current signals. We show how to create, deploy and run the collection of proposed models in a real-time setting using a laptop connected to a test rig via a data acquisition card. Based on a sampling rate of 5 kHz, predictions are stored in an efficient time series database and monitored using a dynamic visualization framework. We further discuss existing options for understanding the decision process behind the predictions made by the models.

Fault Diagnosis of Planetary Gearbox Based on Motor Current Signal Analysis

Planetary gearbox is one of the most widely used core parts in heavy machinery. Once it breaks down, it can lead to serious accidents and economic loss. Induction motor current signal analysis (MCSA) is a noninvasive method that uses current to detect faults. Currently, most MCSA-based fault diagnosis studies focus on the parallel shaft gearbox. However, there is a paucity of studies on the planetary gearbox. The effect of various signal processing methods on motor current and the performance of different machine learning models are rarely compared. Therefore, fault diagnosis of planetary gearbox based MCSA is conducted in this study. First, the effects of various faults on motor currents are studied. Specifically, the characteristic frequencies of a fault in sun/planet/ring gears and supporting bearings of the planetary gearbox are derived. Then, a signal preprocessing method, namely, singular spectrum analysis (SSA), is proposed to remove the supply frequency component in the current signal. Subsequently, four classical machine learning models, including the support vector machine (SVM), decision tree (DT), random forest (RF), and AdaBoost, are used for fault classifications based on the features extracted via principal component analysis (PCA). The convolutional neural network (CNN), which can automatically extract features, is also adopted. The dynamic experiment of the planetary gearbox with seven types of faults, including tooth chipping in sun/planet/ring gears, inner race spall in planet bearing, inner/outer races, and ball spalls in input support bearing, is conducted. Raw current signal in the time domain, reconstructed signal by SSA, and the current spectra in the frequency domain are used as the inputs of various models. The classification results show that the PCA-SVM is the best model for learned data while CNN is the best model for unlearned data on average. Furthermore, SSA mainly increases the accuracy of CNN in the time domain and exhibits a positive effect on unlearned data in the time domain. The classification accuracy increases significantly after transforming the time domain current data to the frequency domain.

Multi-Layer Extreme Learning Machine-Based Keystroke Dynamics Identification for Intelligent Keyboard

Information security plays critical roles in modern society. However, traditional security measures like passwords, tokens and personal ID numbers only provide limited protection. Inspired by the fast training speed of extreme learning machine (ELM) and the promising feature extraction capability of extreme learning machine auto-encoder (ELM-AE), this paper proposes a keystroke dynamics identification method for intelligent keyboard (IKB) based on multi-layer extreme learning machine (ML-ELM). The IKB, as first demonstrated by Wang's group, is a self-powered, non-mechanical perforated keyboard that converts mechanical stimuli applied to the keyboard into electrical signals without the needing an external power source. ML-ELM is a multilayer neural network stacking on top of ELM-AE. Our major contribution is to develop an accurate and efficient keystroke dynamics identification method based on ML-ELM. One significant advantage of the proposed method is that it does not rely on manual feature extraction and selection. In other words, the raw current signals obtained by IKB are directly the input to the network. The network structure is determined by grid search, which minimizes the human involvement. The other one is that the whole training process of the model does not require fine tuning, which makes the training process significantly faster than that of existing deep networks. Experimental results demonstrate that the proposed method has excellent timeliness whereas obtaining high identification accuracy. The proposed method has great potential in applications to computer or network access control, online payment, and cyber security.

Intelligent analysis of tool wear state using stacked denoising autoencoder with online sequential-extreme learning machine

Impeller is a critical component of much large equipment, such as hydropower, nuclear pump, and so on. Its processing quality seriously affects the operation states and service life span of the equipment, while the milling cutter wear determines the processing accuracy of the impeller. Therefore, it is of great important to investigate an intelligent recognition method of tool wear state during the processing. In this research, a new method named stacked denoising autoencoder (SDAE) with online sequential extreme learning machine (OS-ELM) is put forward for intelligent recognition of tool wear states. Firstly, three current signals of the spindle of CNC machine tool are collected during the cutting process and the effective values are synthesized. Then, a new SDAE neural network is trained to acquire the low dimensional features using raw current signals. Finally, OS-ELM is used to realize recognition and classification of the milling cutter, and compared the accuracy with other methods. The method proposed in this paper was verified by both the laboratory signals and the actual engineering signals. The results for spindle current signals show that the developed model has achieved effective performance on tool wear recognition.

An Unsupervised Multiview Sparse Filtering Approach for Current-Based Wind Turbine Gearbox Fault Diagnosis

Gearboxes are critical components in wind turbines, and their fault diagnosis has gained increasing and considerable attention. Compared to traditional vibration-based methods, current-based fault diagnosis has significant advantages in terms of cost, implementation, and reliability. However, it is quite challenging to extract informative fault-related features from raw current signals due to the presence of dominant current fundamental component and harmonic component as well as electrical noise. In order to address this challenge, this article presents a novel unsupervised feature learning approach based on a two-layer sparse filtering algorithm for current-based gearbox fault diagnosis. Specifically, a multiview sparse filtering (MVSF) method is proposed to automatically extract useful and complementary features under different views from raw current signals. The proposed method can fuse multiview feature representations learned concurrently to improve the fault diagnosis performance. The effectiveness of the proposed MVSF method is verified through experiments on a wind turbine gearbox test rig. Experimental results demonstrate that the proposed approach can effectively recognize the health state of the gearbox and exhibits superior performance in feature learning and diagnosis compared with traditional feature extraction approaches.

Accuracy of CMOS-Based Piezoresistive Stress Sensor for Engineering Applications of Thermal Loading Condition: Theoretical Review and Experimental Validation

Measurement uncertainties of a CMOS-based piezoresistive stress sensor are studied for low cycle thermal loading applications. After the fundamentals of the sensor are reviewed briefly, the random uncertainties associated with the data acquisition unit are evaluated first using raw current signals obtained from uniquely fabricated free-standing stress sensor chips. The free-standing sensor chips are tested further for systematic uncertainties associated with the manufacturing-induced residual stresses by subjecting them to a thermal cycle. Finally, the stress measurement accuracy of the sensor chip under an in-situ thermal loading is quantified by a numerical model verified by a sub-micron sensitivity optical technique while incorporating the quantified uncertainties.

Fault Diagnosis System for Induction Motors by CNN Using Empirical Wavelet Transform

Detecting the faults related to the operating condition of induction motors is a very important task for avoiding system failure. In this paper, a novel methodology is demonstrated to detect the working condition of a three-phase induction motor and classify it as a faulty or healthy motor. The electrical current signal data is collected for five different types of fault and one normal operating condition of the induction motors. The first part of the methodology illustrates a pattern recognition technique based on the empirical wavelet transform, to transform the raw current signal into two dimensional (2-D) grayscale images comprising the information related to the faults. Second, a deep CNN (Convolutional Neural Network) model is proposed to automatically extract robust features from the grayscale images to diagnose the faults in the induction motors. The experimental results show that the proposed methodology achieves a competitive accuracy in the fault diagnosis of the induction motors and that it outperformed the traditional statistical and other deep learning methods.