Peng Xiyuan

Online adaptive status prediction strategy for data-driven fault prognostics of complex systems

Accurate fault prediction or remaining useful life (RUL) estimation can obviously reduce cost of maintenance and decrease the probability of accidents so as to improve the performance of the system test and maintenance. At the same time, it is difficult to apply the model-based methods for fault prediction in most applications for complex systems. Due to continuously improving of automation, increasing of sampling frequency and development of computing technology and memory capacity, it gradually promotes data-driven technology into practical methods. Therefore, data-driven fault prognostics based on the sensor or historical test data has become the primary prediction means of complex systems, such as Artificial Neural Networks (ANN), Support Vector Regression (SVR) and other computational intelligence methods. In the other hands, most of traditional forecasting methods are always off-line that are not suitable for on-line prediction and real-time processing. Furthermore, for some on-line prediction methods such as Online Support Vector Regression (Online SVR), there is conflicts and trade-offs between prediction efficiency and accuracy. In real prognostics and health management (PHM) systems, such as the operating status monitoring and forecasting of complex systems like airplane and aircraft, it requires that the algorithms are flexible and adaptive in realization of balance between prediction efficiency and accuracy to meet different complicated requirements. To solve the problem above, an on-line adaptive data-driven fault prognosis and prediction strategy is presented in this paper. Considering the complex characteristics of trends and neighborhood of time series data, the multi-scale reconstruction strategy is applied to effectively reduce the size of on-line data and preserve rich history knowledge of samples. Therefore, the prediction efficiency could be improved and faster forecasting can be achieved with adaptive multi-scale sub-models. To evaluate the proposed prediction strategy, we have executed experiments with Tennessee Eastman (TE) process data. Experimental results with TE process fault data prove its effectiveness. The experiments and tests confirm the algorithms can be effectively applied to the on-line status monitoring and prediction with excellent performance in both efficiency and precision. New on-line fault status prediction strategy shows better prospect in real-time and on-line application for complex system. It can be applied in industrial fields for system maintenance and prognostics and health management.

The design of low-power wireless sensor node

The power consumption of nodes determines the lifetime of the wireless sensor network. Thus, the design of low-power node is very important. With analysis and comparison to various chips in market, we choose MSP430F2618 and CC2520 to build the low-power and high-performance wireless sensor node. The low-power design and control strategy are also considered during the development. We measure and analyze the current consumptions and communication ranges of the node in different working conditions. The experiment results show that the new design has good low-power characteristic and communication performance.

GEMS: A WSN-based greenhouse environment monitoring system

To meet the special requirements on micro-climate raised by the greenhouse in Northeast China, we develop a WSN-based greenhouse environment monitoring system. We decrease the power consumption of nodes, reduce the complexity of system development and simplify the deployment of nodes by dormancy mechanism, single-hop transmission, and on-demand deployment. Gateway node transmits the sensor data to remote database by TD-SCDMA technology. Then, through Internet, people can get access to the environmental information of crops by network terminal. The advantages of this system include low power, low cost, simple structure and flexible extension. The experiments further proved the practicality and reliability of the system.

Fault prediction based on time series with online combined kernel SVR methods

In order to reduce the cost and decrease the probability of accidents, accurate fault prediction is a goal pursued by researchers working at system test and maintenance. Most of traditional fault forecasting methods are not suitable for online prediction and real-time processing. To solve this problem, an online data-driven fault prognosis and prediction method is presented in this paper. The operating states are forecasted with on-line time series prediction model based on the online combined kernel functions Support Vector Regression (SVR). Compared with batch SVR prediction models, online SVR has a good real-time processing performance. However, it is hard for a single kernel SVR to obtain accurate result for the complicated nonlinear and non-stationary time series. Therefore, a combined online SVR with different kernels containing global and local kernels is developed for fault prediction. For general fault modes, the fault trend feature can be extracted by global kernel. On the other hand, local kernel can reflect and revise the local changes of data characteristics in neighborhood. It has realized better result than the method of the single SVR. Experimental results for Tennessee Eastman process fault data prove its effectiveness.

Virtual instrument parameter calibration with particle swarm optimization

In virtual instrument designs and applications, lots of functional parameters can be set through software methods. Currently, most parameter settings methods are lightly linked with the knowledge of instruments and basic principles related to specific applications. However, it is difficult for some end users to deal with those advanced operations. By adopting the particle swarm optimization (PSO) algorithm, the adaptive set and calibration of instrument parameters can be achieved by software with computational intelligence. Experiments and applications showed that the adaptive parameter calibration method based on the PSO can enhance the effectiveness of debugging and maintenance of virtual instrument and test system.

Data-driven framework for lithium-ion battery remaining useful life estimation based on improved nonlinear degradation factor

This paper proposes an improved nonlinear degradation factor based on the current percentage of life-cycle length (CPLL) which contains the battery capacity degradation characteristics information of different periods. This method is improved based on related nonlinear degradation Autoregressive (AR) data-driven prognostics model considering an improved scale nonlinear degradation factor. Then a combination is implemented between the proposed factor and data-driven AR model named nonlinear scale degradation parameter based AR (NSDP-AR) model for better nonlinear prediction ability. Extended Kalman Filter (EKF) is used to obtain the specific factor for certain kind of battery. In order to promote the modified model, a remaining useful life (RUL) prognostic framework using Grey Correlation Analysis (GCA) will be established. The experimental results with the battery data sets from NASA PCoE and CALCE show that the proposed NSDP-AR model and the corresponding prognostic framework can achieve satisfied RUL prediction performance.

Design of FIR Filters with Differential Evolution

Frequency sampling method is one of the usual methods in FIR digital filter design. In frequency sampling method the value of transition band samples are usually obtained by searching for table. However, the value obtained by searching for table can not be ensured to be optimal. In this paper a new application of differential evolution (DE) to frequency sampling method is introduced and its performance is compared to that of genetic algorithm (GA). Experimental results have shown that the value of transition band samples obtained by DE can be ensured to be optimal, also, it is seen that DE is significantly faster than GA for finding the optimum filter.

A Design of Multiprotocol Asynchronous Serial Communication Based on M Module

This paper proposes a design of multi protocol asynchronous serial communication M module, which can be configured as 8-channel RS-232 or 4-channel RS-422/485, and each channels property including baud rate, character-bit, parity mode and stop-bit can be configured separatly through the software. FPGA is adopted as the development platform, using the Verilog HDL to design timing logic of Mbus interface, UART (universal asynchronous receiver transmitter) and control logic of transceiver. This module with multifunction and flexibility, applies to VME, VXI, PXI, LXi and other bus sys-tem. The paper gives the hardware design and driver functions interface. The experimental result indicates that the module works stably, meets the reliability, functional and general requirements.

Traffic Prediction with Reservoir Computing for Mobile Networks

The accurate traffic model and prediction of mobile network plays an important role in network planning. It is particularly important for the performance analysis of mobile networks. The study in this paper concerns predicting the traffic of mobile network, which is essentially nonlinear, dynamic and affected by immeasurable parameters and variables. The accurate analytical model of the traffic of the mobile network can be hardly obtained. Therefore a predicting method based on history input-output using correlation analysis ideas and Reservoir Computing (RC) is proposed. Correlation analysis is used to select proper input variables of the model. Reservoir Computing is a recent research area, in which a random recurrent topology is constructed, and only the weights of connections in a linear output layer is trained. This make it possible to solve complex tasks using just linear post-processing techniques. The proposed model has been verified on the data from network monitoring system in China Mobile Heilongjiang Co. Ltd.

Pre-bond TSV testing method using Constant Current Source

We propose a novel pre-bond TSV test method that covers most of TSV defects before die stacking. The basic idea is to design a DfT structure to acquire the charging voltages of TSVs-under-test, which reflect the characteristics of the defects. The Constant Current Source (CCS) in the proposed structure can improve measurement accuracy and the combining of single-end test and probe-needle-grounding test makes our method has a better defect coverage with high resolution.