Xiaojing Yin

Construction of a new BRB based model for time series forecasting

It is important to predict the future behavior of complex systems. Currently there are no effective methods to solve time series forecasting problem by using the quantitative and qualitative information. Therefore, based on belief rule base (BRB), this paper focuses on developing a new model that can deal with the problem. Although it is difficult to obtain accurately and completely quantitative information, some qualitative information can be collected and represented by a BRB. As such, a new BRB based forecasting model is proposed when the quantitative and qualitative information exist simultaneously. The performance of the proposed model depends on the structure and belief degrees of BRB simultaneously. Moreover, the structure is determined by the delay step. In order to obtain the appropriate delay step using the available information, a model selection criterion is defined according to Akaikes information criterion (AIC). Based on the proposed model selection criterion and the optimal algorithm for training the belief degrees, an algorithm for constructing the BRB based forecasting model is developed. Experimental results show that the constructed BRB based forecasting model can not only predict the time series accurately, but also has the appropriate structure.

A method for predicting the network security situation based on hidden BRB model and revised CMA-ES algorithm

Display Omitted The hidden BRB model is used to predict the network security situation.The observation data of the hidden BRB model is multidimensional.We propose a new constraint CMA-ES algorithm.The revised CMA-ES algorithm is used to optimize the parameters of the hidden BRB model. It is important to establish the forecasting model of the network security situation. But the network security situation cannot be observed directly and can only be measured by other observable data. In this paper the network security situation is considered as a hidden behavior. In order to predict the hidden behavior, some methods have been proposed. However, these methods cannot use the hybrid information that includes qualitative knowledge and quantitative data. As such, a forecasting model of network security situation is proposed on the basis of the hidden belief rule base (BRB) model when the inputs are multidimensional. The initial parameters of the hidden BRB model given by experts may be subjective and inaccurate. In order to train the parameters, a revised covariance matrix adaption evolution strategy (CMA-ES) algorithm is further developed by adding a modified operator. The revised CMA-ES algorithm can optimize the parameters of the hidden BRB model effectively. The case study shows that compared with other methods, the proposed hidden BRB model and the revised CMA-ES algorithm can predict the network security situation effectively to improve the forecasting precision by making full use of qualitative knowledge.

An adaptive denoising fault feature extraction method based on ensemble empirical mode decomposition and the correlation coefficient

Vibration signal processing is commonly used in the mechanical fault diagnosis. It contains abundant working status information. The vibration signal has some features such as non-linear and non-stationary. It has a lot of interference information. Fault information is vulnerable to the impact of the interference information. Empirical mode decomposition denoising method and kurtosis correlation threshold have been widely used in the field of fault diagnosis. But the method mainly depends on the subjective experience, the large number of attempts, and lack of adaptability. In this article, the signals are decomposed into several intrinsic mode functions adaptively with ensemble empirical mode decomposition. The intrinsic mode functions containing the main fault information are selected by the correlation coefficient to emphasize the fault feature and inhibit the normal information. Finally, the energy features of these intrinsic mode functions are taken as inputs of a neural network to identify the fault patterns of rolling bearing. The experiment shows that the neural network diagnosis method based on ensemble empirical mode decomposition has a higher fault recognition rate than based on empirical mode decomposition or wavelet packet method.

The application of multi sensor data fusion based on the improved BP neural network algorithm

In order to improve the accuracy of multi sensor data fusion, a new data fusion algorithm based on BP neural network is proposed, which can prevent the network from not convergence and improve the performance of the network. The calibration data is used as the experimental data which tested in the sensor integrated test stand with Pt100 temperature sensor. The simulation results show that the improved BP neural network for Pt100 temperature sensor data fusion has better accuracy of data fusion compared with the standard BP neural network. The proposed algorithm can be applied in multi-sensor data fusion.

Research on fault diagnosis for rail vehicle compartment of LED lighting system of analog circuit based on WP-EE and BP neural network

A fault diagnosis method based on Wavelet packet energy entropy (WP-EE) and Back Propagation (BP) neural network for the rail vehicle compartment of Light Emitting Diode (LED) lighting system of analog circuit is proposed. In this method, the response signal of the system is decomposed by wavelet packet. To constructed fault characteristic, the WP-EE is extracted. The BP neural network is trained by the sample which has been normalized processing, then import test samples to realize fault diagnosis. The simulation and experimental results show that the method is effective and feasible. The diagnosis is correct and reasonable. And the method has the practical application value.

Hidden behavior prediction of complex systems based on semi-quantitative information

In engineering, it is important to predict hidden behaviors of complex systems. The existing methods for predicting the hidden behavior cannot use semi-quantitative information. As such, in this paper a new BRB based model is proposed to predict the hidden behavior. In the proposed BRB based model, the initial values of parameters are usually given by experts, thus some of them may not be accurate, which can lead to inaccurate prediction results. In order to solve the problem, a parameter estimation algorithm for training the parameters of the forecasting model is further proposed on the basis of maximum likelihood (ML) algorithm. A case study is conducted to demonstrate the capability and potential applications of the proposed forecasting model with the parameter estimation algorithm.

A new health estimation model for CNC machine tool based on infinite irrelevance and belief rule base

Abstract To guarantee the normal workflow and determine scheme of optimal maintenance, it is important to accurately estimate the health condition of computerized numerical control (CNC) machine tool. In current studies, the health condition of CNC machine tool is modeled by using one feature. Due to the complexity of CNC machine tool, the estimating accuracy of the current models is poor and real-time performance cannot be satisfied when multiple features are chosen. Moreover, it is difficult to obtain more effective monitoring data when the CNC machine tool is from normal to failure. To solve the problems, based on infinite irrelevance and belief rule base (BRB), a health estimation model which is named as the infinite irrelevance BRB model is proposed in this paper. In particular, the infinite irrelevance method is used to select key features to optimize the model structure, and BRB is applied to estimate the health condition according to the monitoring data and expert knowledge. Thus, the quantitative monitoring data and expert knowledge can be used effectively to improve accuracy and real-time performance of health estimation. Furthermore, because the initial values of the parameters in the proposed infinite irrelevance BRB model given by experts may not be accurate, the constraint covariance matrix adaptation evolution strategy (CMA-ES) algorithm is employed to train the parameters. A case study for the servo system of the CNC milling machine is used to verify the effective and accuracy of the proposed model. The results show that the infinite irrelevance BRB model can accurately estimate the health condition of the servo system.

A New BRB Model for Cloud Security-State Prediction Based on the Large-Scale Monitoring Data

Considering the reliability of the cloud computing system, this paper aims to predict the security state with multiple large-scale attributes in cloud computing system. A double-layer method for predicting the security state of cloud computing system based on the belief rule-base model is proposed, where the evidential reasoning (ER) algorithm is employed to fuse the multiple system indicators of actual cloud system and make a reasonable assessment to describe the cloud security state. This method can utilize quantitative and qualitative information simultaneously. By using the ER algorithm to integrate multiple indicators whose attributes contain much uncertain information, the security state of the cloud computing system can be predicted accurately. Moreover, due to the initial parameters of the proposed models are given by experts that might cause imprecise results, the constraint CMA-ES algorithm is employed as the optimization tool to obtain the optimal parameters. A practical study about the cloud security-state prediction is verified to indicate the potential applications about the proposed prediction model in a cloud computing platform.

A novel health estimation model for CNC machine tool servo system based on belief-rule-base

Health condition estimation is an important means to guarantee the normal work and the optimal maintenance for CNC machine tool servo system. The health condition is denoted by features. In order to estimate the health condition for servo system, belief-rule-base (BRB) model is employed as estimation method in this paper. This method can composite multiple knowledge including some uncertain information to improve the accuracy of health condition estimation. Because of the multiplicity of the feature parameters, infinite irrelevance method is used to extract main characteristics. As the initial knowledge by experts is not accurate enough, CMA-ES is used to optimize the parameters in BRB. The case study show that the model can estimate the health of servo system accurately.

A Double Layer BRB Model for Health Prognostics in Complex Electromechanical System

The health of a complex electromechanical system is dynamic and is accompanied by a full life cycle. Due to the complexity and coupling of complex electromechanical systems, the establishment of a dynamic and accurate model for the health state is difficult. A belief rule base (BRB) shows outstanding performance in modeling complex systems because it can combine both quantitative information and expert knowledge. In this paper, a double-layer BRB model is proposed to predict the health state of a complex electromechanical system. The two layers achieve different functions: BRB_layer1 is used to establish the dynamic change of the time series of features, BRB_layer2 is employed to combine the features for predicting the health state of the complex electromechanical system. During this process, the infinite irrelevance method is utilized for feature selection in reducing the scale of the BRB model. Considering the initial parameters are given by experts, which may have boundedness and may not be appropriate for engineering practice, the projection covariance matrix adaption evolution strategy (P-CMA-ES) is chosen as the optimization algorithm to train the initial parameters. To verify the rationality and effectiveness of the proposed model, the low-frequency vibration fault of a certain aero-engine is taken as an example. The results show that the proposed method can predict the health state of a complex electromechanical system precisely according to current and historical data.