A Sensor Failure Detection Method Based on Artificial Neural Network and Signal Processing

This paper proposes a sensor failure detection method based on artificial neural network and signal processing,in comparison with other methods,which does not need any redundancy information among sensor outputs and divides the output of a sensor into'Signal dominant component'and'Noise dominant component'because the pattern of sensor failure often appears in the'Noise dominant component'.With an ARMA model built for'Noise dominant component'using artificial neural network,such sensor failures as bias failure,hard failure,drift failure,spike failure and cyclic failure may be detected through residual analysis,and the type of sensor failure can be indicated by an appropriate indicator.The failure detection procedure for a temperature sensor in a hovercraft engine is simulated to prove the applicability of the method proposed in this paper.

Neural Network Signal Processing Approach for Damage Assessment in Fiberoptic Smart Material Systems and Structures

An approach by using neural network signal processing in associate with embedded fiberoptic sensing array for the newly developed “smart material systems and structures” is discussed in this paper.The principle,structure of this approach and suitable neural network algorithms are described.The results of simulation experiments are also given.

GENERALIZED INVERSE GROUP OF SIGNAL AND ITS IMPLEMENTATION WITH NEURAL NETWORKS

A new concept, the generalized inverse group (GIG) of signal, is firstly proposed and its properties, leaking coefficients and implementation with neural networks are presented. Theoretical analysis and computational simulation have shown that (1) there is a group of finite length of generalized inverse signals for any given finite signal, which forms the GIG; (2) each inverse group has different leaking coefficients, thus different abnormal states; (3) each GIG can be implemented by a grouped and improved single-layer perceptron which appears with fast convergence. When used in deconvolution, the proposed GIG can form a new parallel finite length of filtering deconvolution method. On off-line processing, the computational time is reduced to O(N) from O(N2). And the less the leaking coefficient is, the more reliable the deconvolution will be.

A VIBRATION RECOGNITION METHOD BASED ON DEEP LEARNING AND SIGNAL PROCESSING

Effective vibration recognition can improve the performance of vibration control and structural damage detection and is in high demand for signal processing and advanced classification.Signal-processing methods can extract the potent time-frequency-domain characteristics of signals;however,the performance of conventional characteristics-based classification needs to be improved.Widely used deep learning algorithms(e.g.,convolutional neural networks(CNNs))can conduct classification by extracting high-dimensional data features,with outstanding performance.Hence,combining the advantages of signal processing and deep-learning algorithms can significantly enhance vibration recognition performance.A novel vibration recognition method based on signal processing and deep neural networks is proposed herein.First,environmental vibration signals are collected;then,signal processing is conducted to obtain the coefficient matrices of the time-frequency-domain characteristics using three typical algorithms:the wavelet transform,Hilbert-Huang transform,and Mel frequency cepstral coefficient extraction method.Subsequently,CNNs,long short-term memory(LSTM)networks,and combined deep CNN-LSTM networks are trained for vibration recognition,according to the time-frequencydomain characteristics.Finally,the performance of the trained deep neural networks is evaluated and validated.The results confirm the effectiveness of the proposed vibration recognition method combining signal preprocessing and deep learning.

WiFi CSI Gesture Recognition Based on Parallel LSTM-FCN Deep Space-Time Neural Network

In this study,we developed a system based on deep space–time neural networks for gesture recognition.When users change or the number of gesture categories increases,the accuracy of gesture recognition decreases considerably because most gesture recognition systems cannot accommodate both user differentiation and gesture diversity.To overcome the limitations of existing methods,we designed a onedimensional parallel long short-term memory–fully convolutional network(LSTM–FCN)model to extract gesture features of different dimensions.LSTM can learn complex time dynamic information,whereas FCN can predict gestures efficiently by extracting the deep,abstract features of gestures in the spatial dimension.In the experiment,50 types of gestures of five users were collected and evaluated.The experimental results demonstrate the effectiveness of this system and robustness to various gestures and individual changes.Statistical analysis of the recognition results indicated that an average accuracy of approximately 98.9% was achieved.

Speed-Sensorless Control Using Elman Neural Network

This paper describes a modified speed-sensorless control for induction motor (IM) based on space vector pulse width modulation and neural network. An Elman ANN method to identify the IM speed is proposed, with IM parameters employed as associated elements. The BP algorithm is used to provide an adaptive estimation of the motor speed. The effectiveness of the proposed method is verified by simulation results. The implementation on TMS320F240 fixed DSP is provided.

Artificial Intelligence for Speech Recognition Based on Neural Networks

Speech recognition or speech to text includes capturing and digitizing the sound waves, transformation of basic linguistic units or phonemes, constructing words from phonemes and contextually analyzing the words to ensure the correct spelling of words that sounds the same. Approach: Studying the possibility of designing a software system using one of the techniques of artificial intelligence applications neuron networks where this system is able to distinguish the sound signals and neural networks of irregular users. Fixed weights are trained on those forms first and then the system gives the output match for each of these formats and high speed. The proposed neural network study is based on solutions of speech recognition tasks, detecting signals using angular modulation and detection of modulated techniques.

PWM VLSI Neural Network for Fault Diagnosis

An improved pulse width modulation (PWM) neural network VLSI circuit for fault diagnosis is presented, which differs from the software-based fault diagnosis approach and exploits the merits of neural network VLSI circuit. A simple synapse multiplier is introduced, which has high precision, large linear range and less switching noise effects. A voltage-mode sigmoid circuit with adjustable gain is introduced for realization of different neuron activation functions. A voltage-pulse conversion circuit required for PWM is also introduced, which has high conversion precision and linearity. These 3 circuits are used to design a PWM VLSI neural network circuit to solve noise fault diagnosis for a main bearing. It can classify the fault samples directly. After signal processing, feature extraction and neural network computation for the analog noise signals including fault information,each output capacitor voltage value of VLSI circuit can be obtained, which represents Euclid distance between the corresponding fault signal template and the diagnosing signal, The real-time online recognition of noise fault signal can also be realized.

An Optimal Method for Speech Recognition Based on Neural Network

Natural language processing technologies have become more widely available in recent years,making them more useful in everyday situations.Machine learning systems that employ accessible datasets and corporate work to serve the whole spectrum of problems addressed in computational linguistics have lately yielded a number of promising breakthroughs.These methods were particularly advantageous for regional languages,as they were provided with cut-ting-edge language processing tools as soon as the requisite corporate information was generated.The bulk of modern people are unconcerned about the importance of reading.Reading aloud,on the other hand,is an effective technique for nour-ishing feelings as well as a necessary skill in the learning process.This paper pro-posed a novel approach for speech recognition based on neural networks.The attention mechanism isfirst utilized to determine the speech accuracy andfluency assessments,with the spectrum map as the feature extraction input.To increase phoneme identification accuracy,reading precision,for example,employs a new type of deep speech.It makes use of the exportchapter tool,which provides a corpus,as well as the TensorFlow framework in the experimental setting.The experimentalfindings reveal that the suggested model can more effectively assess spoken speech accuracy and readingfluency than the old model,and its evalua-tion model’s score outcomes are more accurate.

Classification of Ultrasonic Signs Pre-processed by Fourier Transform through Artificial Neural Network Using the Echo Pulse Technique for the Identification of Defects in Welded Joints of Structural Steel

It is due to the need to ensure the security and integrity of equipment, that the non-destructive tests have been increasingly used in the industrial sector. Among these, the ultrasonic pulse echo technique is the most used in industry, mainly for its simplicity and efficiency. With one transducer only, it is possible to emit the ultrasonic and receive the echo pulse. The ANNs （artificial neural networks） are artificial intelligence techniques that, when properly trained, align themselves to inspection tests becoming a powerful tool in the detection and fault identification. In this work, the echo pulse technique was used to detect discontinuities in welds, where ANNs were fed from the information obtained by digital signal processing techniques （Fourier transform）, to identify and classify three distinct classes of defects. Results showed that with the combination of feature extraction by Fourier transformation and classification with neural networks, it is possible to obtain an automatic defect detection system in welded joints with average efficiency.

A New Pattern Recognition Method for Detection and Localization of Myocardial Infarction Using T-Wave Integral and Total Integral as Extracted Features from One Cycle of ECG Signal

In this paper we used two new features i.e. T-wave integral and total integral as extracted feature from one cycle of normal and patient ECG signals to detection and localization of myocardial infarction (MI) in left ventricle of heart. In our previous work we used some features of body surface potential map data for this aim. But we know the standard ECG is more popular, so we focused our detection and localization of MI on standard ECG. We use the T-wave integral because this feature is important impression of T-wave in MI. The second feature in this research is total integral of one ECG cycle, because we believe that the MI affects the morphology of the ECG signal which leads to total integral changes. We used some pattern recognition method such as Artificial Neural Network (ANN) to detect and localize the MI, because this method has very good accuracy for classification of normal signal and abnormal signal. We used one type of Radial Basis Function (RBF) that called Probabilistic Neural Network (PNN) because of its nonlinearity property, and used other classifier such as k-Nearest Neighbors (KNN), Multilayer Perceptron (MLP) and Naive Bayes Classification. We used PhysioNet database as our training and test data. We reached over 76% for accuracy in test data for localization and over 94% for detection of MI. Main advantages of our method are simplicity and its good accuracy. Also we can improve the accuracy of classification by adding more features in this method. A simple method based on using only two features which were extracted from standard ECG is presented and has good accuracy in MI localization.

Enhancing Parkinson’s Disease Diagnosis Accuracy Through Speech Signal Algorithm Modeling

Parkinson’s disease(PD),one of whose symptoms is dysphonia,is a prevalent neurodegenerative disease.The use of outdated diagnosis techniques,which yield inaccurate and unreliable results,continues to represent an obstacle in early-stage detection and diagnosis for clinical professionals in the medical field.To solve this issue,the study proposes using machine learning and deep learning models to analyze processed speech signals of patients’voice recordings.Datasets of these processed speech signals were obtained and experimented on by random forest and logistic regression classifiers.Results were highly successful,with 90%accuracy produced by the random forest classifier and 81.5%by the logistic regression classifier.Furthermore,a deep neural network was implemented to investigate if such variation in method could add to the findings.It proved to be effective,as the neural network yielded an accuracy of nearly 92%.Such results suggest that it is possible to accurately diagnose early-stage PD through merely testing patients’voices.This research calls for a revolutionary diagnostic approach in decision support systems,and is the first step in a market-wide implementation of healthcare software dedicated to the aid of clinicians in early diagnosis of PD.

VOICE/NON-VOICE DISCRIMINATION SYSTEM FOR PUBLIC COMMUNICATION NETWORKS

The features of non-voice signals on public communication nets are analyzed and an approach to distinguish such signals is introduced in this paper. It is the first time for the system to meet three key targets: large-scale, high recognition rate and low false alarm at the same time.

基于模糊神经网络的电网消防预警算法

针对传统基于阈值判别方法的电网火灾预警系统预测精度低、抗干扰能力弱的问题,提出了一种基于模糊神经网络的电网消防预警算法。该算法利用神经网络学习大规模电网数据,使用模糊逻辑推理算法来提升预测结果的推理能力,并通过结合神经网络对大规模数据的学习能力和模糊逻辑算法的推理能力来分析电网线路参数,从而提升电网消防预警系统的精度和抗干扰能力。实验与仿真结果表明,所提出方法能显著提升电网火灾的预警精度,且使用模糊逻辑推理可以得到更符合实际情况的电网火灾预警结果。

基于图的点云研究综述

点云的处理、传输、语义分割等是3维计算机视觉领域重要的分析任务.现如今,图神经网络和图结构在点云研究方面的有效性已被证实,基于图的点云(graph-based point cloud,GPC)研究不断涌现.因此,一种统一的研究角度、框架和方法论亟待形成.系统性梳理了GPC研究的各种应用场景,包括配准、降噪、压缩、表示学习、分类、分割、检测等任务,概括出GPC研究的一般性框架,提出了一条覆盖当前GPC全域研究的技术路线.具体来说,给出了GPC研究的分层概念范畴,包括底层数据处理、中层表示学习、高层识别任务;综述了各领域中的GPC模型或算法,包括静态和动态点云的处理算法、有监督和无监督的表示学习模型、传统或机器学习的GPC识别算法;总结了其中代表性的成果及其核心思想,譬如动态更新每层特征空间对应的最近邻图、分层以及参数共享的动态点聚合模块,结合图划分和图卷积提高分割精度;对比了模型性能,包括总体精度(overall accuracy,OA)、平均精度(mean accuracy,mAcc)、平均交并比(mean intersection over union,mIoU);在分析比较现有模型和方法的基础上,归纳了GPC目前面临的主要挑战,提出相应的研究问题,并展望未来的研究方向.建立的GPC研究框架具有一般性和通用性,为后续研究者从事GPC这个新型交叉领域研究提供了领域定位、技术总结及宏观视角.点云研究的出现,是探测器硬件技术长足进步后应运而生的结果;点云研究的现状表明在理论和实践之间存在一些挑战,一些关键问题还有待解决.同时,点云研究的发展将推动人工智能进入新的时代.

基于混合神经网络的多维视觉传感信号模式分类

传感器采集的数字信号分类精度差,导致关键信息的丢失。为了提高传感数据的可靠性和有效性,提出基于混合神经网络的多维视觉传感信号模式分类方法。结合卷积神经网络(CNN)、循环神经网络(RNN)构建混合神经网络,以更有效地表示多维视觉数据中的特征;其中,卷积神经网络负责对多维的空间信号进行去噪处理并提取特征;循环神经网络负责对时域和频域信号进行特征提取;混合神经网络通过联合训练CNN和RNN各自的参数,以调整其权重,并且结合两者从不同层级提取的特征来实现多维视觉传感信号模式的分类。仿真结果表明,使用所提方法进行分类时,信号光滑度保持在0.9以上,传感信号分类结果与实际结果拟合度较高,有效实现多维视觉传感信号模式分类。

电力电缆局放在线监测神经网络自动识别精度的提升方法

为了尽可能降低电缆线路局放在线监测系统装置运行中对局放信号识别的误判误报的可能性,对局放的判读机理和识别精度进行了改进和提升。基于现场运行系统回收的数万个疑似电缆内部局放的告警记录数据进行了分析分类,对判别程序中沿用的局放自动逻辑判别程序追加了相间信号相关性过滤程序,对既有的神经网络在构造上作了优选优化,对神经网络学习数据的前置处理进行了改进。对改进提升后的局放判别程序采用了包括现场记录,模拟信号发生器和人工局放模型加电压实验的3种局放数据进行检验。结果表明,改进提升后的局放判别程序不但能够使现场的非局放告警数据的告警率降低到5%的期待水平,同时也提高了识别人工模拟产生的各种类型局放信号的准确性,大大降低了局放在线监测系统误判误报的可能性。

机械设备电气故障自动检测系统优化设计

当前系统不能有效消除干扰信号,数据采集精度低,影响机械设备电气故障诊断,为此设计一种新的机械设备电气故障自动检测系统。采集电气故障检测数据,提取电气故障特征,根据特征判断机械设备的电气故障原因,计算纠正参数完善电气故障检测结果,线性处理电压检测曲线,完成机械设备电气故障检测。测试结果验证,所提系统能够有效消除干扰信号,保证整体功能运行稳定,相对于对比系统,响应时间更短,数据采集精度得到明显改善。

基于电子鼻和电子舌与1D-CNN-LSTM模型的花椒产地快速溯源检测

针对不同产地花椒产品的溯源问题,提出一种基于电子鼻和电子舌结合一维卷积神经网络(One Dimension-Convolutional Neural Networks,1D-CNN)-长短期记忆网络(Long Short-Term Memory,LSTM)混合模型的花椒产地快速检测方法。以5个不同产地的花椒为试验对象,采用电子舌和电子鼻分别采集花椒样本的味觉和嗅觉指纹图谱信息,根据信号特点分别设计1D-CNN提取味觉和嗅觉信号中的局部空间特征,然后采用LSTM捕捉信号的时间序列特征,最后采用多层感知机融合两种特征并进行分类识别。实验结果表明,电子鼻与电子舌信息融合对不同产地花椒的分辨准确率优于单一设备,与其他深度模型相比,所提的模型分类准确性更高,其准确率、精确率、召回率、F1分数分别达到99.0%、99.1%、99.0%、0.989。以上研究将为不同产地花椒的快速鉴定提供新的方法,并为其他农产品的产地溯源检测提供新的研究思路。