Communication simulation of on-board diagnosis network in high-speed Maglev trains

The on-board diagnosis network is the nervous system of high-speed Maglev trains, connecting all controller sensors, and corresponding devices to realize the information acquisition and control. In order to study the on-board diagnosis network＇s security and reliability, a simulation model for the on-board diagnosis network of high-speed Maglev trains with the optimal network engineering tool （OPNET） was built to analyze the network＇s performance, such as response error and bit error rate on the network load, throughput, and node-state response. The simulation model was verified with an actual on-board diagnosis network structure. The results show that the model results obtained are in good agreement with actual system performance and can be used to achieve actual communication network optimization and control algorithms.

Fault Diagnosis for Manifold Absolute Pressure Sensor(MAP) of Diesel Engine Based on Elman Neural Network Observer

Intake system of diesel engine is a strong nonlinear system, and it is difficult to establish accurate model of intake system; and bias fault and precision degradation fault of MAP of diesel engine can＇t be diagnosed easily using model-based methods. Thus, a fault diagnosis method based on Elman neural network observer is proposed. By comparing simulation results of intake pressure based on BP network and Elman neural network, lower sampling error magnitude is gained using Elman neural network, and the error is less volatile. Forecast accuracy is between 0.015？0.017 5 and sample error is controlled within 0？0.07. Considering the output stability and complexity of solving comprehensively, Elman neural network with a single hidden layer and with 44 nodes is presented as intake system observer. By comparing the relations of confidence intervals of the residual value between the measured and predicted values, error variance and failures in various fault types. Then four typical MAP faults of diesel engine can be diagnosed： complete failure fault, bias fault, precision degradation fault and drift fault. The simulation results show： intake pressure is observable and selection of diagnostic strategy parameter reasonably can increase the accuracy of diagnosis;the proposed fault diagnosis method only depends on data and structural parameters of observer, not depends on the nonlinear model of air intake system. A fault diagnosis method is proposed not depending system model to observe intake pressure, and bias fault and precision degradation fault of MAP of diesel engine can be diagnosed based on residuals.

Diagnosabilities of exchanged hypercube networks under the pessimistic one-step diagnosis strategy

The exchanged hypercube EH（s, t） （where s ≥ 1 and t ≥ 1） is obtained by systematically reducing links from a regular hypercube Q,＋t＋l. One-step diagnosis of exchanged hypercubes which involves only one testing phase during which processors test each other is discussed. The diagnosabilities of exchanged hypercubes are studied by using the pessimistic one-step diagno- sis strategy under two kinds of diagnosis models： the PMC model and the MM model. The main results presented here are the two proofs that the degree of diagnosability of the EH（s, t） under pessimistic one-step tl/tl fault diagnosis strategy is 2s where I ≤ s ≤ t （respectively, 2t, where 1 ≤ t ≤ s） based on the PMC model and that it is also 2s where 1 ≤ s ≤ t （respectively, 2t, where 1 ≤ t ≤ s） based on the MM＊ model.

SEQUENTIAL DIAGNOSIS FOR A CENTRIFUGAL PUMP BASED ON FUZZY NEURAL NETWORK

A sequential diagnosis method is proposed based on a fuzzy neural network realized by ＂the partially-linearized neural network （PNN）＂, by which the fault types of rotating machinery can be precisely and effectively distinguished at an early stage on the basis of the possibilities of symptom parameters. The non-dimensional symptom parameters in time domain are defined for reflecting the features of time signals measured for the fault diagnosis of rotating machinery. The synthetic detection index is also proposed to evaluate the sensitivity of non-dimensional symptom parameters for detecting faults. The practical example of condition diagnosis for detecting and distinguishing fault states of a centrifugal pump system, such as cavitation, impeller eccentricity which often occur in a centrifugal pump system, are shown to verify the efficiency of the method proposed in this paper.

PerfMon: Measuring Application-Level Performance in a Large-Scale Campus Wireless Network

WiFi has become one of the most popular ways to access the Internet.However,in large-scale campus wireless networks,it is challenging for network administrators to provide optimized access quality without knowledge on fine-grained traffic characteristics and real network performance.In this paper,we implement PerfMon,a network performance measurement and diagnosis system,which integrates collected multi-source datasets and analysis methods.Based on PerfMon,we first conduct a comprehensive measurement on application-level traffic patterns and behaviors from multiple dimensions in the wireless network of T university(TWLAN),which is one of the largest campus wireless networks.Then we systematically study the application-level network performance.We observe that the application-level traffic behaviors and performance vary greatly across different locations and device types.The performance is far from satisfactory in some cases.To diagnose these problems,we distinguish locations and device types,and further locate the most crucial factors that affect the performance.The results of case studies show that the influential factors can effectively characterize performance changes and explain for performance degradation.

APPROACH TO FAULT ON-LINE DETECTION AND DIAGNOSIS BASED ON NEURAL NETWORKS FOR ROBOT IN FMS

Based on radial basis function (RBF) neural networks, the healthy working model of each sub system of robot in FMS is established. A new approach to fault on line detection and diagnosis according to neural networks model is presented. Fault double detection based on neural network model and threshold judgement and quick fault identification based on multi layer feedforward neural networks are applied, which can meet quickness and reliability of fault detection and diagnosis for robot in FMS.

Diagnosis of Intermittent Connections for DeviceNet

An intermittent connection is one of the major problems that affect the network reliability and communication quality.However,little attention has been paid to the detection,analysis and localization of the intermittent connections.Partially due to the limitations of the DeviceNet protocol,there is no effective online diagnostic tool available to identify the location of intermittent connection.On the basis of different DeviceNet fault scenarios induced by intermittent connections,a new graph-based diagnostic method is developed to analyze DeviceNet fault patterns,identify the corresponding fault scenarios,and infer the location of the intermittent connection problem by using passively captured network faults.A novel error source analysis tool,which integrates network data-link layer analysis and feature based network physical layer information,is developed to restore the snapshots of the network communication at each intermittent connection induced error.A graph based location identification method is developed to infer the location of the intermittent connections based on the restored error patterns.A 3-node laboratory test-bed,using master-slave polling communication method,is constructed to emulate the intermittent connection induced faults on the network drop cable by using digital switches,whose on/off states are controlled by a computer.During experiments,the network fault diagnosis is conducted by using information collected on trunk cable（backbone）.Experimental study shows that the proposed method is effective to restore the snapshots of the network errors and locate the drop cable that experiences the intermittent connection problem.

CONDITION MONITOR OF DEEP-HOLE DRILLING BASED ON MULTI-SENSOR INFORMATION FUSION

A condition monitoring method of deep-hole drilling based on multi-sensor information fusion is discussed. The signal of vibration and cutting force are collected when the condition of deep-hole drilling on stainless steel 0Cr17Ni4Cu4Nb is normal or abnormal. Four eigenvectors are extracted on time-domain and frequency-domain analysis of the signals. Then the four eigenvectors are combined and sent to neural networks to dispose. The fusion results indicate that multi-sensor information fusion is superior to single-sensor information, and that cutting force signal can reflect the condition of cutting tool better than vibration signal.

DIAGNOSABILITY OF CAYLEY GRAPH NETWORKS GENERATED BY TRANSPOSITION TREES UNDER THE COMPARISON DIAGNOSIS MODEL

Diagnosability of a multiprocessor system is one important study topic.Cayley graph network Cay（Tn,Sn） generated by transposition trees Tnis one of the attractive underlying topologies for the multiprocessor system.In this paper,it is proved that diagnosability of Cay（Tn,Sn） is n-1 under the comparison diagnosis model for n ≥ 4.

RESEARCH ON EXPERT SYSTEM OF FAULT DETECTION AND DIAGNOSING FOR PNEUMATIC SYSTEM OF AUTOMATIC PRODUCTION LINE

Fault detection and diagnosis for pneumatic system of automatic productionline are studied. An expert system using fuzzy-neural network and pneumatic circuit fault diagnosisinstrument are deigned. The mathematical model of various pneumatic faults and experimental deviceare built. In the end, some experiments are done, which shows that the expert system usingfuzzy-neural network can diagnose fast and truly fault of pneumatic circuit.

An efficient lossy link localization approach for wireless sensor networks

Network fault management is crucial for a wireless sensor network(WSN) to maintain a normal running state because faults(e.g., link failures) often occur. The existing lossy link localization(LLL) approach usually infers the most probable failed link set first, and then gives the fault hypothesis set. However, the inferred failed link set contains many possible failures that do not actually occur. That quantity of redundant information in the inferred set can pose a high computational burden on fault hypothesis inference, and consequently decreases the evaluation accuracy and increases the failure localization time. To address the issue, we propose the conditional information entropy based redundancy elimination(CIERE), a redundant lossy link elimination approach, which can eliminate most redundant information while reserving the important information. Specifically, we develop a probabilistically correlated failure model that can accurately reflect the correlation between link failures and model the nondeterministic fault propagation. Through several rounds of mathematical derivations, the LLL problem is transformed to a set-covering problem. A heuristic algorithm is proposed to deduce the failure hypothesis set. We compare the performance of the proposed approach with those of existing LLL methods in simulation and on a real WSN, and validate the efficiency and effectiveness of the proposed approach.

Implementation of Envelope Analysis on a Wireless Condition Monitoring System for Bearing Fault Diagnosis

Envelope analysis is an effective method for characterizing impulsive vibrations in wired condition monitoring(CM)systems. This paper depicts the implementation of envelope analysis on a wireless sensor node for obtaining a more convenient and reliable CM system. To maintain CM performances under the constraints of resources available in the cost effective Zigbee based wireless sensor network(WSN), a low cost cortex-M4 F microcontroller is employed as the core processor to implement the envelope analysis algorithm on the sensor node. The on-chip 12 bit analog-to-digital converter(ADC) working at 10 k Hz sampling rate is adopted to acquire vibration signals measured by a wide frequency band piezoelectric accelerometer. The data processing flow inside the processor is optimized to satisfy the large memory usage in implementing fast Fourier transform(FFT) and Hilbert transform(HT). Thus, the envelope spectrum can be computed from a data frame of 2048 points to achieve a frequency resolution acceptable for identifying the characteristic frequencies of different bearing faults. Experimental evaluation results show that the embedded envelope analysis algorithm can successfully diagnose the simulated bearing faults and the data transmission throughput can be reduced by at least 95% per frame compared with that of the raw data, allowing a large number of sensor nodes to be deployed in the network for real time monitoring.