摘要:
At present, system-level fault detection and diagnosis (FDD) research often uses correlation-based machine learning methods combined with multiple heterogeneous diagnosis methods to improve the fault detection rate (FDR), that is, decision-level fusion. Since it does not take into account the causal direction of the decision relationship, it will affect the realization of the fusion objectives, and lead to the reduction of the fusion range and the decrease of the global decision on FDR. In this regard, the structural causal model (SCM), a commonly used causal model in causal science, can use the causal graph to ensure causal direction of fusion, and the structural equation can be used to achieve fusion objectives to increase FDR, which can improve this problem. In this paper, we propose seven fusion objectives according to the diagnostic advantage interval of each preliminary method, and use SCM to construct causal graph and structural equation to achieve decision-level fusion according to the proposed seven fusion objectives, thereby improving FDR. The proposed method is validated through the simulation platform Tennessee Eastman process. We choose to combine the prediction results of Linear Discriminant Analysis method and Gaussian Naive Bayes method to achieve decision-level fusion. The results show that compared with the single method and the Bayesian network decision-level fusion method, the proposed method can achieve the best results in the FDR of each single system state and average FDR, and the above indicators are significantly improved.
作者机构:
[Ma, Jiayu; Huang, Jiahui; Liu, Jie; Yang, Xiaohua] School of Computer Science, University of South China, Hunan, Hengyang, China;[Liu, Hua] School of Electrical Engineering, University of South China, Hunan, Hengyang, China
通讯机构:
[Liu, J.; Yang, X.] S;School of Computer Science, Hunan, China
关键词:
compensation response;fault diagnosis;information flow;inverse response;SDG model
摘要:
Visual inspection techniques for rail surface defects have become prevalent approaches to obtain information on rail surface damage. However, uneven illumination leads to illegibility of local information, and the change of the wheel-rail area results in the changeful background of the rail surface, both of which pose challenges to the visual inspection. This paper proposes a novel algorithm that detects rail surface defects via partitioned edge features (PEF). PEF eliminates the effect of uneven illumination by effectively extracting edge features and building homogeneous background on the rail surface. In the process of edge feature extraction, the thresholding based on adaptive partition of rail surface (APRS) plays an indispensable role. In APRS, the rail surface is adaptively partitioned into three types of regions according to the wheel-rail contact degree. After that, the dynamic threshold is set adaptively for each region type on the basis of the prior information of defect proportion. Subsequently, based on neighborhood information and fuzzy decision, the spatial information of adjacent pixels and the direction information of fracture edges are utilized to realize the effective recovery of incomplete defect contours. In addition, defect contours are precisely filled via a flexible combination of morphological hole filling operation and defect region extraction based on improved background difference. The accuracy of this PEF algorithm was confirmed by experiments and comparisons with related algorithms. The experiment results show that PEF detects defects with 92.03% recall and 88.49% precision, which achieves higher accuracy than the established detection algorithms for rail surface defects.
摘要:
Dynamically measuring rail profile using the structured-light vision suffers from random vibrations on the line laser projector, which would cause distorted rail profiles. This paper presents a simple and effective distortion rectifying method to address this issue. The distorted rail profile is rectified by easily projecting it onto an auxiliary plane which is parallel to the cross section of rail. In order to establish the auxiliary plane, three profiles formed by radiating multiline structured light on rail are used to fit the rail longitudinal axis. More importantly, only one of the light planes is required to be calibrated beforehand. The others are calibrated online with the proposed self-calibration method, which is based on collinearity and parallelity constraints on the scene points of different rail profiles and requires only one image of the scene. Apart from evaluating the implementation with comprehensive experiments, we compare our method against other published works. The results exhibit its effectiveness and superiority in terms of the dynamic measurement of the rail profile.
期刊:
PROCEEDINGS OF THE 26TH INTERNATIONAL CONFERENCE ON NUCLEAR ENGINEERING, 2018, VOL 1,2018年1
通讯作者:
Liu, Hua
作者机构:
[Liu, Hua; Li, Meng; Liu, Zhao-hui; Yang, Xiao-Hua] Univ South China, CNNC Key Lab High Trusted Comp, Hengyang, Peoples R China.;[Chen, Zhi] Nucl Power Inst CHINA, Chengdu, Sichuan, Peoples R China.;[Zhao, Qing; Feng, Zhigang] Univ South China, Sch Elect Engn, Heng Yang City, Hunan, Peoples R China.
通讯机构:
[Liu, Hua] U;Univ South China, CNNC Key Lab High Trusted Comp, Hengyang, Peoples R China.
会议名称:
26th International Conference on Nuclear Engineering (ICONE-26)
会议时间:
JUL 22-26, 2018
会议地点:
London, ENGLAND
会议主办单位:
[Liu, Hua;Yang, Xiao-Hua;Liu, Zhao-hui;Li, Meng] Univ South China, CNNC Key Lab High Trusted Comp, Hengyang, Peoples R China.^[Chen, Zhi] Nucl Power Inst CHINA, Chengdu, Sichuan, Peoples R China.^[Feng, Zhigang;Zhao, Qing] Univ South China, Sch Elect Engn, Heng Yang City, Hunan, Peoples R China.
关键词:
Digital instrument control platform;Information security;Vulnerability analysis;Security loophole
摘要:
Structured-light vision (SLV) is a standard approach for inspecting rail wear. However, it is incompetent for dynamic inspection due to the random vibrations in the line laser projector. In this paper, a three-step distortion rectifying method is introduced to address this issue. Given an image with two rail profile stripes, the first step involves parallelity constraint-based establishment of an auxiliary plane whose normal vector is parallel with the rail longitudinal axis. The establishment is only dependent on the intrinsic camera parameters, which improves the robustness of the auxiliary plane to the random vibrations in the line laser projector. In step two, this auxiliary plane is utilized for the autonomous calibration of the line structured lights. The proposed self-calibration is achieved by minimizing the point set mapping errors on triple matching primitives such as rail jaw, railhead inner, and rail foot and requires only two laser stripes. After these two steps, two rail profiles are reconstructed from the double-line SLV without known poses, and the distorted one is projected onto the auxiliary plane for distortion rectifying. It is able to deliver more precise rectifying than the parallel-line SLV and cross-line SLV, even if the inspecting task is performed dynamically. With the comprehensive experiments, we test our scheme and compare it with the related methods. The experimental results verify that the proposed method outperforms the previous works in terms of the accuracy and robustness for the dynamic wear inspection.
作者机构:
[刘华] School of Electrical Engineering, University of South China, Hengyang;Hunan;421001, China;[韩文兴; 陈智] Nuclear Power Institute of CHINA, Chengdu;610041, China
作者机构:
[Liu, Hua] Univ South China, Sch Elect Engn, Heng Yang City, Hunan, Peoples R China.;[Yan, Shiyu; Liu, Zhaohui; Yang, Xiaohua] Univ South China, CNNC Key Lab High Trusted Comp, Heng Yang City, Hunan, Peoples R China.;[Chen, Zhi] Nucl Power Inst CHINA, Chengdu, Sichuan, Peoples R China.
会议名称:
26th International Conference on Nuclear Engineering (ICONE-26)
会议时间:
JUL 22-26, 2018
会议地点:
London, ENGLAND
会议主办单位:
[Liu, Hua] Univ South China, Sch Elect Engn, Heng Yang City, Hunan, Peoples R China.^[Liu, Zhaohui;Yang, Xiaohua;Yan, Shiyu] Univ South China, CNNC Key Lab High Trusted Comp, Heng Yang City, Hunan, Peoples R China.^[Chen, Zhi] Nucl Power Inst CHINA, Chengdu, Sichuan, Peoples R China.
会议论文集名称:
Proceedings of the 2018 26th International Conference on Nuclear Engineering
摘要:
In the design phase of digital instrument control system, the reactor scram subsystem is a complex system that is constructed by hardware, software, system interaction and communication. So the single analysis method such as FMEA and FTA are all have limitations. FMEA and FTA are all based in the accident model with event chain. FTA is not suitable for the discovery of software and communication failures and other problems with high coupling degree, time series association, constraints of control. Three independent basic analysis methods, FMEA, FTA and STPA, are combined to form the statistical table of failure and failure coverage. For FMEA and FTA, the design safety problem detection rate is only 74.1% and 64% respectively for reactor scram subsystem. The detection rate of STPA for reactor SCRAM subsystem is up to 95.1%. Meanwhile, multiple method fusion can cover all the safety issues triggered by hardware, software, system interaction, and communication failure and defect. The analysis of this paper shows that multiple method fusion is better than single method. STPA method is superior to other single security analysis methods. STPA method can effectively make up for the inadequacy of FMEA and FTA method.