量子–经典混合神经网络及其故障诊断应用

量子神经网络由于结合了量子计算和神经网络的优点, 近年来受到了广泛的关注. 然而由于目前量子计算 资源受限(如量子比特数、量子逻辑门的保真度等)以及贫瘠高原现象(量子神经网络优化过程中解空间变得平坦时 出现的训练困难)的存在, 量子神经网络当前还难以大规模训练. 针对上述问题, 本文面向量子–经典混合神经网络 模型提出了一种基于无监督学习的特征提取方法. 所采用的无监督学习方法结合了量子自编码器和K-medoids聚类 方法, 可用于多层次结构的特征学习. 该方法创新地利用了K-mediods方法对训练得到的量子自编码器进行聚类, 以 最大化量子自编码器性质的差异. 进一步, 本文在轴承异常检测问题上, 通过实验验证了所提出的无监督特征提取 方法的有效性和实用性, 测试集准确率在二分类、四分类和十分类分别达到100%, 89.6%和81.6%.     

代价敏感概率神经网络及其在故障诊断中的应用

针对传统的分类算法人多以误分率最小化为目标,忽略了误分类型之间的差别和数据集的非平衡性的问题,提出代价敏感概率神经网络算法.该算法将代价敏感机制引入概率神经网络,用期望代价取代误分率,以期望代价最小化为目标,基于期望代价最小的贝叶斯决策规则预测新样本类别.采用工业现场数据和数据集German Credit验证了该算法的有效性.实验结果表明,该算法具有故障识别率高、泛化能力强、建模时间短等特点.     

Closed-loop fault diagnosis based on a nonlinear process model and automatic fuzzy rule generation

In this contribution a new approach for fault detection and diagnosis (FDD) for nonlinear processes is presented. A nonlinear fuzzy model with transparent inner structure is used for the generation of relevant symptoms. The resulting symptom patterns are classified with a new self-learning classification structure based on fuzzy rules. The approach is successfully applied to an electro-pneumatic valve in a closed control loop.     

FPNN:优化的过程神经网络模型及其应用

利用既定条件下过程神经元与傅里叶神经元的等价性,提出一种优化的过程神经网络模型FPNN,并对等价性进行了证明。FPNN网络在保持了过程神经网络模型表达能力和预测准确率的同时,继承了FNN的优点,大大提高了模型的效率。     

A modular neural network approach to fault diagnosis

Certain real-world applications present serious challenges to conventional neural-network design procedures. Blindly trying to train huge networks may lead to unsatisfactory results and wrong conclusions about the type of problems that can be tackled using that technology. In this paper a modular solution to power systems alarm handling and fault diagnosis is described that overcomes the limitations of "toy" alternatives constrained to small and fixed-topology electrical networks. In contrast to monolithic diagnosis systems, the neural-network-based approach presented here accomplishes the scalability and dynamic adaptability requirements of the application. Mapping the power grid onto a set of interconnected modules that model the functional behavior of electrical equipment provides the flexibility and speed demanded by the problem. After a preliminary generation of candidate fault locations, competition among hypotheses results in a fully justified diagnosis that may include simultaneous faults. The way in which the neural system is conceived allows for a natural parallel implementation.     

基于规则获取的Petri网诊断模型设计

通过旋转机械故障诊断规则的获取分析,讨论了利用诊断规则设计Petri网诊断模型的方法.该模型的设计建立在简化的样本集基础上,可有效降低Petri网的复杂程度,避免Petri网在复杂系统建模时出现的组合爆炸问题;针对诊断规则的形式,定义并提出将诊断规则转换为标准基本规则序列,便于模型的程序化设计;同时诊断规则的获取可以有效推广故障诊断范围,使其不仅仅局限于样本集,并能消除样本集中存在的不一致问题带来的影响.通过示例证明了这种方法的可行性与有效性,并给出了相关算法.     

A neural network and fuzzy rule base hybrid for pattern classification

 This paper presents a novel hybrid of the two complimentary technologies of soft computing viz. neural networks and fuzzy logic to design a fuzzy rule based pattern classifier for problems with higher dimensional feature spaces. The neural network component of the hybrid, which acts as a pre-processor, is designed to take care of the all-important issue of feature selection. To circumvent the disadvantages of the popular back propagation algorithm to train the neural network, a meta-heuristic viz. threshold accepting (TA) has been used instead. Then, a fuzzy rule based classifier takes over the classification task with a reduced feature set. A combinatorial optimisation problem is formulated to minimise the number of rules in the classifier while guaranteeing high classification power. A modified threshold accepting algorithm proposed elsewhere by the authors (Ravi V, Zimmermann H.-J. (2000) Eur J Oper Res 123: 16–28) has been employed to solve this optimization problem. The proposed methodology has been demonstrated for (1) the wine classification problem having 13 features and (2) the Wisconsin breast cancer determination problem having 9 features. On the basis of these examples the results seem to be very interesting, as there is no reduction in the classification power in either of the problems, despite the fact that some of the original features have been completely eliminated from the study. On the contrary, the chosen features in both the problems yielded 100% classification power in some cases.     

对传过程神经元网络及其应用研究

基于传统对传神经元网络在时域上推广,构造出对传过程神经元网络模型,并对对传过程神经元网络模型及其学习算法进行研究。最后将对传过程神经元网络模型应用到油层水淹识别实例上,模拟仿真结果表明了模型和算法的有效性。     

基于混合卷积神经网络和循环神经网络的入侵检测模型

针对电力信息网络中的高级持续性威胁问题,提出一种基于混合卷积神经网络（CNN）和循环神经网络（RNN）的入侵检测模型。该模型根据网络数据流量的统计特征对当前网络状态进行分类。首先,获取日志文件中网络流量的各统计值,进行特征编码、归一化等预处理工作;然后,通过深度卷积神经网络中可变卷积核提取不同主机入侵流量之间空间相关特征;最后,将已经处理好的包含空间相关特征的数据在时间上错开排列,利用深度循环神经网络挖掘入侵流量的时间相关特征。实验结果表明,该模型相对于传统的机器学习模型在曲线下方的面积（AUC）上提升了7.5%~14.0%,同时误报率降低了83.7%~52.7%。所提模型能准确地识别网络流量的类别,大幅降低误报率。     

A fuzzy neural network approach for online fault detection in waste water treatment process

In this paper, an effective strategy for fault detection of sludge volume index (SVI) sensor is proposed and tested on an experimental hardware setup in waste water treatment process (WWTP). The main objective of this fault detection strategy is to design a system which consists of the online sensors, the SVI predicting plant and fault diagnosis method. The SVI predicting plant is designed utilizing a fuzzy neural network (FNN), which is trained by a historical set of data collected during fault-free operation of WWTP. The fault diagnosis method, based on the difference between the measured concentration values and FNN predictions, allows a quick revealing of the faults. Then this proposed fault detection method is applied to a real WWTP and compared with other approaches. Experimental results show that the proposed fault detection strategy can obtain the fault signals of the SVI sensor online.     

A novel data-based quality-related fault diagnosis scheme for fault detection and root cause diagnosis with application to hot strip mill process

In this paper, a new technology or solution of quality-related fault diagnosis is provided for hot strip mill process (HSMP). Different from traditional data-based fault diagnosis methods, the alternative approach is focused more on root cause diagnosis. The new scheme addresses the quality-related fault detection with the developed modified canonical variable analysis (MCVA) model, then the advantage of original generalized reconstruction based contribution (GRBC) is followed to identify the faulty variables. Meanwhile, a new transfer entropy (TE)-based causality analysis method is proposed for root cause diagnosis of quality-related faults. Finally, the whole proposed framework is practiced with real HSMP data, and the results demonstrate the usage and effectiveness of these approaches.     

A hybrid fault diagnosis strategy for chemical process startups

Development of fault detection and diagnosis has been emphasized for industrial processes in order to reduce process downtimes and maintain high quality products with reduced environmental effects. Faults occur more frequently during process startups due to dramatic state variations and tendency of manual operation, and it is therefore vital to diagnose and correct any faults efficiently during process startups. In this paper, a new fault diagnosis method for process startups is developed using on-line dynamic time warping technique in combination with the principal component analysis. SymCure reasoning under the G2 Optegrity is integrated to the strategy so that the method is able to diagnose new faults unknown to historical data. The proposed method was tested on startups of a lab-scale distillation column. Results indicate that it can diagnose both known and unknown faults effectively with improved computational efficiency.     

A hybrid fault diagnosis approach using neural networks

A hybrid fault diagnosis method is proposed in this paper which is based on the parity equations and neural networks. Analytical redundancy is employed by using parity equations. Neural networks then are used to maximise the signal- to- noise ratio of the residual and to isolate different faults. Effectiveness of the method is demonstrated by applying it to fault detection and isolation for a hydraulic test rig. Real data simulation shows that the sensitivity of the residual to the faults is maximised, whilst that to the unknown input is minimised. The simulated faults are successfully isolated by a bank of neural nets.     

基于神经网络的化工过程故障诊断

由于化工过程的高复杂性及高危险性,且装置都是都是长周期连续运转,一旦出现故障会造成巨大的损失,因此对化工过程和设备进行早期和准确的故障检测与诊断,可以提高设备运行的安全性,避免发生重大安全事故,降低生产成本.人工神经网络具有非线性、大规模、并行处理能力强,以及鲁棒性、容错性、自学习能力强等特点,处理化工过程的复杂非线性问题,比其他方法都优越.本文描述了人工神经网络的基本原理,及近年来人工神经网络在化工过程故障诊断应用中的进展.以BP神经网络为例,分析和介绍了其结构和学习算法,说明了神经网络故障诊断的推理过程,并建议将神经网络与符号有向图(SDG)结合诊断故障.     

A hybrid model of partial least squares and neural network for traffic incident detection

Development of a universal freeway incident detection algorithm is a task that remains unfulfilled and many promising approaches have been recently explored. The partial least squares (PLS) method and artificial neural network (NN) were found in previous studies to yield superior incident detection performance. In this article, a hybrid model which combines PLS and NN is developed to detect automatically traffic incident. A real traffic data set collected from motorways A12 in the Netherlands is presented to illustrate such an approach. Data cleansing has been introduced to preprocess traffic data sets to improve the data quality in order to increase the veracity and reliability of incident model. The detection performance is evaluated by the common criteria including detection rate, false alarm rate, mean time to detection, classification rate and the area under the curve (AUC) of the receiver operating characteristic. Computational results indicate that the hybrid approach is capable of increasing detection performance comparing to PLS, and simplifying the NN structure for incident detection. The hybrid model is a promising alternative to the usual PLS or NN for incident detection.     

灰色神经网络模型及其应用

灰色建模要求的样本点少,不必有较好的分布规律,而且计算量少,操作简便。而BP网络学习样本时,会反馈校正输出的误差,具有并行计算、分布式信息存储、强容错力、自适应学习功能等优点。本文将灰色预测建模和神经网络技术融合起来,建立灰色神经网络模型(GNNM)。提出计算残差序列和新的预测值的公式。用于发酵动力学预测,结果表明,灰色神经网络模型在预测精度方面优于常规灰色模型。该模型的算法概念明确,计算简便,有较高的拟合和预测精度,拓宽了灰色模型的应用范围。     

一类基于神经网络非线性观测器的鲁棒故障检测和诊断

利用神经网络的非线性建模能力，对一类具有建模不确定项的非线性系统提出一种基于观测器的故障检测和诊断的方法。设计的观测器不仅能实现故障检测，而旦应用神经网络设计的故障估计器能在线估计系统中的故障向量。通过分析验证了该方法对系统中的建模误差和外部扰动具有良好的鲁棒性。仿真结果表明所提出的方法是有效的。     

A Neural Network Appraoch to Fault Diagnosis in Analog Circuits

Thia paper presents a neural network based fault diagnosis approach for analog circuits,taking the tolerances of circuit elements into account.Specifically,a normalization rule of input information,a pseudo-fault domain border(PFDB)pattern selection method and a new output error function are proposed for training the backpropagation(BP) network to be a fault diagnoser.Experimental results demonstrate that the diagnoser performs as well as or better than any classical approaches in terms of accuracy,and provides at least an order-of-magnitude improvement in post-fault diagnostic speed.     

A modified hybrid neural network for pattern recognition and its application to SSW complex in EEG

In this study, a modified hybrid neural network with asymmetric basis functions is presented for feature extraction of spike and slow wave complexes in electroencephalography (EEG). Feature extraction process has a great importance in all pattern recognition and classification problems. A gradient descent algorithm, indeed a back propagation type, is adapted to the proposed artificial neural network. The performance of the proposed network is measured using a support vector machine classifier fed by features extracted using the proposed neural network. The results show that the proposed neural network model can effectively be used in pattern recognition tasks. In experiments, real EEG data are used.     

A neural network model for fault detection in conjunction with a programmable logic controller

This paper discusses the feasibility of using neural networks as a tool in the fault detection process. A neural network is integrated with a state language programmable logic controller, an important device in an automatic control system. Time series data related to time spent in a state is gathered and used as input into a neural network, for the purpose of identifying when a fault has occurred. A feedforward neural network is used to identify which (if any) of three types of faults may have occurred. Experimental results related to sensitivity and accuracy measures are presented. A brief review of related applications and research is also presented.