ENGINE SENSOR FAULT DIAGNOSIS USING MAIN AND DECENTRALIZED NEURAL NETWORKS

This Paper presents a methodology for solving the sensor failure detection, isolation and accommodation of aeroengine control systems using on line learning neural networks(NN), which has one main NN and a set of decentralized NNs. Changes in the system dynamics are monitored by the on line learning NN. When a failure occurs in some sensor, the sensor failure detection can be accomplished with high precision, and the sensor failure accommodation can be achieved by replacing the value from the failed sensor with its estimate from the decentralized NN. By integrating the optimal estimation and failure logic, this method can detect soft failures. Simulation of one kind of turboshaft engine control system with this multiple neural network architecture shows that the ANN developed can detect and isolate hard and soft sensor failures timely and provide accurate accommodation.

SENSOR FAILURE DETECTION AND SIGNAL RECOVERY BASED ON BP NEURAL NETWORK

A study is given on the application of BP neural network (BPNN) in sensorfailure detection in control systems, and on the networ architecture desgn, the redun-dancy,the quickness and the insensitivity to sensor noise of the BPNN based sensor detec-tion methed. Besules, an exploration is made into tbe factors accounting for the quality ofsignal recovery for failed sensor using BPNN. The results reveal clearly that BPNN can besuccessfully used in sensor failure detection and data recovery.

STOCHASTIC NEURAL NETWORK AND ITS APPLICATION TO MULTI－MANEUVERING TARGET TRACKING

ＳＴＯＣＨＡＳＴＩＣＮＥＵＲＡＬＮＥＴＷＯＲＫＡＮＤＩＴＳＡＰＰＬＩＣＡＴＩＯＮＴＯＭＵＬＴＩ－ＭＡＮＥＵＶＥＲＩＮＧＴＡＲＧＥＴＴＲＡＣＫＩＮＧＪｉｎｇＺｈｏｎｇｌｉａｎｇ；ＤａｉＧｕａｎｚｈｏｎｇ；ＴｏｎｇＭｉｎｇａｎ；ＺｈｏｕＨｏｎｇｒｅｎ（Ｄ...

Electroluminescence Device to Implement the Clipped Hopfield Neural Network

The method,which used an electroluminescent device to implement the clipped Hopfield neural network,is presented in detail.The electroluminescence devices are used to represent the neurons and the photodetectors are used to represent the connection matrix.The characteristics of the electroluminescence device and the photodetector are tested.And the characteristics of this system is discussed briefly.

Hamilton Number Neural Network Model

The stability and the sequential dynamics of the sixteen-state Hamiltnn neural network model have been discussed with the energy function. The optical implementation scheme about Hamilton number vector-matrix multiplication is simply discussed.

Analysis of Texture of Froth Image in Coal Flotation

Froth image features of coal flotation have been extracted and studied by neighboring grey level dependence matrix, spatial grey level dependence matrix and grey level histogram. In this paper, a basic algorithm of unsupervised learning pattern classification is presented, and coal flotation froth images are classified by means of self organizing map (SOM). By extracting features from 51 flotation froth images with laboratory column, four types of froth images are classified. The correct rate of SOM cluster is satisfactory. And a good relationship of froth type with average ash content is also observed.

Artificial Intelligence Embedded Object-Oriented Methodology For Model Based Decision Support

The paper presents the coupling of artificial intelligence-AI and Object-oriented methodology applied for the construction of the model-based decision support system MBDSS.The MBDSS is designed for support the strategic decision making lead to the achievemellt of optimal path towardsmarket economy from the central planning situation in China. To meet user's various requirements,a series of innovations in software development have been carried out, such as system formalization with OBFRAMEs in an object-oriented paradigm for problem solving automation and techniques of modules intelligent cooperation, hybrid system of reasoning, connectionist framework utilization,etc. Integration technology has been highly emphasized and discussed in this article and an outlook to future software engineering is given in the conclusion section.

Mobile Memory Management System Based on User’s Application Usage Patterns

Currently,the number of functions to improve user convenience in smartphone applications is increasing.In addition,more mobile applications are being loaded into mobile operating system memory for faster launches,thus increasing the memory requirements for smartphones.The memory used by applications in mobile operating systems is managed using software;allocated memory is freed up by either considering the usage state of the application or terminating the least recently used(LRU)application.As LRU-based memory management schemes do not consider the application launch frequency in a low memory situation,currently used mobile operating systems can lead to the termination of a frequently executed application,thereby increasing its relaunch time.This study proposes a memory management system that can efficiently utilize the main memory space by analyzing the application usage information.The proposed system reduces the application launch time by leaving the most frequently used or likely to be run applications in the main memory for as long as possible.The performance evaluation conducted utilizing actual smartphone usage records showed that the proposed memory management system increases the number of times the applications resume from the main memory compared with the conventional memory management system,and that the average application execution time is reduced by approximately 17%.

Storage capacity of complex Hopfield model

The Dirac symbol is used to represent the discrete complex Hopfield neural network model.The signal-to-noise theory and the computer numerical solution are made to analyse the storage capacity of the model.The storage capacity ratio of the model equals to that of the Hopfield model.Finally,using the model to recognize the 4-level grey or color patterns is discussed.

Novel Fiberoptic Sensing Array and Fundamental Experiments

A suitable fiberoptic sensing array embedded in the smart structure to monitor quasi-distributed forces on the structure is presented in this paper.Artificial nearal networks are used in processing of fiberoptic sensing array signals.Fundamental experiments have been done and the results are also given.

Remarks on the Efficiency of Bionic Optimisation Strategies

Bionic optimisation is one of the most popular and efficient applications of bionic engineering. As there are many different approaches and terms being used, we try to come up with a structuring of the strategies and compare the efficiency of the different methods. The methods mostly proposed in literature may be classified into evolutionary, particle swarm and artificial neural net optimisation. Some related classes have to be mentioned as the non-sexual fern optimisation and the response surfaces, which are close to the neuron nets. To come up with a measure of the efficiency that allows to take into account some of the published results the technical optimisation problems were derived from the ones given in literature. They deal with elastic studies of frame structures, as the computing time for each individual is very short. General proposals, which approach to use may not be given. It seems to be a good idea to learn about the applicability of the different methods at different problem classes and then do the optimisation according to these experiences. Furthermore in many cases there is some evidence that switching from one method to another improves the performance. Finally the identification of the exact position of the optimum by gradient methods is often more efficient than long random walks around local maxima.

Analytic design of information granulation-based fuzzy radial basis function neural networks with the aid of multiobjective particle swarm optimization

Purpose–The purpose of this paper is to consider the concept of Fuzzy Radial Basis Function Neural Networks with Information Granulation(IG-FRBFNN)and their optimization realized by means of the Multiobjective Particle Swarm Optimization(MOPSO).Design/methodology/approach–In fuzzy modeling,complexity,interpretability(or simplicity)as well as accuracy of the obtained model are essential design criteria.Since the performance of the IG-RBFNN model is directly affected by some parameters,such as the fuzzification coefficient used in the FCM,the number of rules and the orders of the polynomials in the consequent parts of the rules,the authors carry out both structural as well as parametric optimization of the network.A multi-objective Particle Swarm Optimization using Crowding Distance(MOPSO-CD)as well as O/WLS learning-based optimization are exploited to carry out the structural and parametric optimization of the model,respectively,while the optimization is of multiobjective character as it is aimed at the simultaneous minimization of complexity and maximization of accuracy.Findings–The performance of the proposed model is illustrated with the aid of three examples.The proposed optimization method leads to an accurate and highly interpretable fuzzy model.Originality/value–A MOPSO-CD as well as O/WLS learning-based optimization are exploited,respectively,to carry out the structural and parametric optimization of the model.As a result,the proposed methodology is interesting for designing an accurate and highly interpretable fuzzy model.

Exponential stability for impulsive Cohen-Grossberg neural networks with time-varying delays and distributed delays

Purpose–The purpose of this paper is to develop a methodology for the existence and global exponential stability of the unique equilibrium point of a class of impulsive Cohen-Grossberg neural networks.Design/methodology/approach–The authors perform M-matrix theory and homeomorphism mapping principle to investigate a class of impulsive Cohen-Grossberg networks with time-varying delays and distributed delays.The approach builds on new sufficient criterion without strict conditions imposed on self-regulation functions.Findings–The authors’approach results in new sufficient criteria easy to verify but without the usual assumption that the activation functions are bounded and the time-varying delays are differentiable.An example shows the effectiveness and superiority of the obtained results over some previously known results.Originality/value–The novelty of the proposed approach lies in removing the usual assumption that the activation functions are bounded and the time-varying delays are differentiable,and the use of M-matrix theory and homeomorphism mapping principle for the existence and global exponential stability of the unique equilibrium point of a class of impulsive Cohen-Grossberg neural networks.

Research on the mechanical fault diagnosis method based on sound signal and IEMD-DDCNN

Purpose–The purpose of this paper is to provide a shorter time cost,high-accuracy fault diagnosis method for water pumps.Water pumps are widely used in industrial equipment and their fault diagnosis is gaining increasing attention.Considering the time-consuming empirical mode decomposition(EMD)method and the more efficient classification provided by the convolutional neural network(CNN)method,a novel classification method based on incomplete empirical mode decomposition(IEMD)and dual-input dual-channel convolutional neural network(DDCNN)composite data is proposed and applied to the fault diagnosis of water pumps.Design/methodology/approach–This paper proposes a data preprocessing method using IEMD combined with mel-frequency cepstrum coefficient(MFCC)and a neural network model of DDCNN.First,the sound signal is decomposed by IEMD to get numerous intrinsic mode functions(IMFs)and a residual(RES).Several IMFs and one RES are then extracted by MFCC features.Ultimately,the obtained features are split into two channels(IMFs one channel;RES one channel)and input into DDCNN.Findings–The Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection(MIMII dataset)is used to verify the practicability of the method.Experimental results show that decomposition into an IMF is optimal when taking into account the real-time and accuracy of the diagnosis.Compared with EMD,51.52% of data preprocessing time,67.25% of network training time and 63.7%of test time are saved and also improve accuracy.Research limitations/implications–This method can achieve higher accuracy in fault diagnosis with a shorter time cost.Therefore,the fault diagnosis of equipment based on the sound signal in the factory has certain feasibility and research importance.Originality/value–This method provides a feasible method for mechanical fault diagnosis based on sound signals in industrial applications.

On-line RNN compensated second order nonsingular terminal sliding mode control for hypersonic vehicle

Purpose–The purpose of this paper is to design a robust control scheme to achieve robust tracking of velocity and altitude commands for a general hypersonic vehicle(HSV)in the presence of parameter variations and external disturbances.Design/methodology/approach–The robust control scheme is composed of nonsingular terminal sliding mode control(NTSMC),super twisting control algorithm(STC)and recurrent neural network(RNN).First,by combing a novel NTSMC and STC algorithm,a second order NTSMC approach for HSV is proposed to provide fast,continuous and high precision tracking control.Second to relax the requirements for the bounds of the lumped uncertainties in control design,a RNN disturbance observer is presented to increase the robustness of the control system.The weights of RNN are updated by adaptive laws based on Lyapunov theorem,thus the closed-loop stability can be guaranteed.Findings–Simulation results demonstrate that the proposed method is effective,leading to promising performance.Originality/value–The main contributions of this work are:first,both parameter variations and external disturbances are considered in control design for the longitudinal dynamic model of HSV;and second,the proposed controller can remove chattering and achieve more favorable tracking performances than conventional sliding mode control.

Auto-regressive multiple-valued logic neurons with sequential Chua’s oscillator back-propagation learning for online prediction and synchronization of chaotic trajectories

Purpose–The purpose of this paper is to examine the structural and computational potentials of a powerful class of neural networks(NNs),called multiple-valued logic neural networks(MVLNN),for predicting the behavior of phenomenological systems with highly nonlinear dynamics.MVLNNs are constructed based on the integration of a number of neurons working based on the principle of multiple-valued logics.MVLNNs possess some particular features,namely complex-valued weights,input,and outputs coded by kth roots of unity,and a continuous activation as a mean for transferring numbers from complex spaces to trigonometric spaces,which distinguish them from most of the existing NNs.Design/methodology/approach–The presented study can be categorized into three sections.At the first part,the authors attempt at providing the mathematical formulations required for the implementation of ARX-based MVLNN(AMVLNN).In this context,it is indicated that how the concept of ARX can be used to revise the structure of MVLNN for online applications.Besides,the stepwise formulation for the simulation of Chua’s oscillatory map and multiple-valued logic-based BP are given.Through an analysis,some interesting characteristics of the Chua’s map,including a number of possible attractors of the state and sequences generated as a function of time,are given.Findings–Based on a throughout simulation as well as a comprehensive numerical comparative study,some important features of AMVLNN are demonstrated.The simulation results indicate that AMVLNN can be employed as a tool for the online identification of highly nonlinear dynamic systems.Furthermore,the results show the compatibility of the Chua’s oscillatory system with BP for an effective tuning of the synaptic weights.The results also unveil the potentials of AMVLNN as a fast,robust,and efficient control-oriented model at the heart of NMPC control schemes.Originality/value–This study presents two innovative propositions.First,the structure of MVLNN is modified based on the concept of ARX system identification programming to suit the base structure for coping with chaotic and highly nonlinear systems.Second,the authors share the findings about the learning characteristics of MVLNNs.Through an exhaustive comparative study and considering different rival methodologies,a novel and efficient double-stage learning strategy is proposed which remarkably improves the performance of MVLNNs.Finally,the authors describe the outline of a novel formulation which prepares the proposed AMVLNN for applications in NMPC controllers for dynamic systems.