A multi-layer approach to DN 50 electric valve fault diagnosis using shallow-deep intelligent models

Liu, Yong-kuo,Zhou, Wen,Ayodeji, Abiodun,Zhou, Xin-qiu,Peng, Min-jun,Chao, Nan Korean Nuclear Society 2021 Nuclear Engineering and Technology Vol.53 No.1

Timely fault identification is important for safe and reliable operation of the electric valve system. Many research works have utilized different data-driven approach for fault diagnosis in complex systems. However, they do not consider specific characteristics of critical control components such as electric valves. This work presents an integrated shallow-deep fault diagnostic model, developed based on signals extracted from DN50 electric valve. First, the local optimal issue of particle swarm optimization algorithm is solved by optimizing the weight search capability, the particle speed, and position update strategy. Then, to develop a shallow diagnostic model, the modified particle swarm algorithm is combined with support vector machine to form a hybrid improved particle swarm-support vector machine (IPs-SVM). To decouple the influence of the background noise, the wavelet packet transform method is used to reconstruct the vibration signal. Thereafter, the IPs-SVM is used to classify phase imbalance and damaged valve faults, and the performance was evaluated against other models developed using the conventional SVM and particle swarm optimized SVM. Secondly, three different deep belief network (DBN) models are developed, using different acoustic signal structures: raw signal, wavelet transformed signal and time-series (sequential) signal. The models are developed to estimate internal leakage sizes in the electric valve. The predictive performance of the DBN and the evaluation results of the proposed IPs-SVM are also presented in this paper.

A new perspective towards the development of robust data-driven intrusion detection for industrial control systems

Ayodeji, Abiodun,Liu, Yong-kuo,Chao, Nan,Yang, Li-qun Korean Nuclear Society 2020 Nuclear Engineering and Technology Vol.52 No.12

Most of the machine learning-based intrusion detection tools developed for Industrial Control Systems (ICS) are trained on network packet captures, and they rely on monitoring network layer traffic alone for intrusion detection. This approach produces weak intrusion detection systems, as ICS cyber-attacks have a real and significant impact on the process variables. A limited number of researchers consider integrating process measurements. However, in complex systems, process variable changes could result from different combinations of abnormal occurrences. This paper examines recent advances in intrusion detection algorithms, their limitations, challenges and the status of their application in critical infrastructures. We also introduce the discussion on the similarities and conflicts observed in the development of machine learning tools and techniques for fault diagnosis and cybersecurity in the protection of complex systems and the need to establish a clear difference between them. As a case study, we discuss special characteristics in nuclear power control systems and the factors that constraint the direct integration of security algorithms. Moreover, we discuss data reliability issues and present references and direct URL to recent open-source data repositories to aid researchers in developing data-driven ICS intrusion detection systems.

Support vector ensemble for incipient fault diagnosis in nuclear plant components

Abiodun Ayodeji,Yong-kuo Liu 한국원자력학회 2018 Nuclear Engineering and Technology Vol.50 No.8

The randomness and incipient nature of certain faults in reactor systems warrant a robust and dynamicdetection mechanism. Existing models and methods for fault diagnosis using different mathematical/statistical inferences lack incipient and novel faults detection capability. To this end, we propose a faultdiagnosis method that utilizes the flexibility of data-driven Support Vector Machine (SVM) forcomponent-level fault diagnosis. The technique integrates separately-built, separately-trained, specializedSVM modules capable of component-level fault diagnosis into a coherent intelligent system, witheach SVM module monitoring sub-units of the reactor coolant system. To evaluate the model, marginalfaults selected from the failure mode and effect analysis (FMEA) are simulated in the steam generator andpressure boundary of the Chinese CNP300 PWR (Qinshan I NPP) reactor coolant system, using a bestestimatethermal-hydraulic code, RELAP5/SCDAP Mod4.0. Multiclass SVM model is trained withcomponent level parameters that represent the steady state and selected faults in the components. Foroptimization purposes, we considered and compared the performances of different multiclass models inMATLAB, using different coding matrices, as well as different kernel functions on the representative dataderived from the simulation of Qinshan I NPP. An optimum predictive model - the Error CorrectingOutput Code (ECOC) with TenaryComplete coding matrix - was obtained from experiments, and utilizedto diagnose the incipient faults. Some of the important diagnostic results and heuristic model evaluationmethods are presented in this paper

DL-RRT* Algorithm for Least Dose Path Re-planning in Dynamic Radioactive Environments

Nan Chao,Yong-kuo Liu,HONG XIA,Min-jun Peng,Abiodun Ayodeji 한국원자력학회 2019 Nuclear Engineering and Technology Vol.51 No.3

One of the most challenging safety precautions for workers in dynamic, radioactive environments isavoiding radiation sources and sustaining low exposure. This paper presents a sampling-based algorithm,DL-RRT*, for minimum dose walk-path re-planning in radioactive environments, expedient for occupationalworkers in nuclear facilities to avoid unnecessary radiation exposure. The method combines theprinciple of random tree star (RRT*) and D* Lite, and uses the expansion strength of grid search strategyfrom D* Lite to quickly find a high-quality initial path to accelerate convergence rate in RRT*. The algorithminherits probabilistic completeness and asymptotic optimality from RRT* to refine the existingpaths continually by sampling the search-graph obtained from the grid search process. It can not only beapplied to continuous cost spaces, but also make full use of the last planning information to avoid globalre-planning, so as to improve the efficiency of path planning in frequently changing environments. Theeffectiveness and superiority of the proposed method was verified by simulating radiation field undervarying obstacles and radioactive environments, and the results were compared with RRT* algorithmoutput.

Association of 8 Loci on Chromosome 8q24 with Prostate Carcinoma Risk in Northern Chinese Men

Zhao, Cheng-Xiao,Liu, Ming,Wang, Jian-Ye,Xu, Yong,Wei, Dong,Yang, Kuo,Yang, Ze Asian Pacific Journal of Cancer Prevention 2013 Asian Pacific journal of cancer prevention Vol.14 No.11

Multiple genetic studies have confirmed association of 8q24 variants with susceptibility to prostate cancer (PCa). As PCa risk SNPs may also influence disease outcome, we studied here eight 8q24 risk alleles, and evaluated their role in PCa clinical covariates in northern Chinese men. Blood samples and clinical information were collected from ethnically Chinese men from Northern China with histologically-confirmed PCa (n=289) and from age-matched normal controls (n=288). Eight 8q24 SNPs were genotyped by polymerase chain reaction-high- resolution melting analysis in 577 subjects. We examined the prevalence distribution of 8q24 risk alleles and analyzed the associations between the risk allele and PCa and clinical covariates to infer their impact on aggressive PCa. Three of the eight SNPs were associated with PCa risk in northern Chinese men, including rs16901966 (OR 1.31, 95% CI 1.01-1.70, p=0.042), rs1447295 (OR 1.47, 95% CI 1.09-1.98, p=0.011) and rs10090154 (OR 1.55, 95% CI 1.14-2.12, p=0.005). Haplotype analysis based association with the risk alleles revealed significant differences between cases and controls (OR 1.43, 95%CI 0.99-2.06, p=0.049). The risk alleles rs16901966, rs1447295 and rs10090154 were associated with age at diagnosis and tumor stage as compared with controls, while rs16901966 was associated with aggressive PCa (OR 1.43, 95% CI 1.01-2.03, p=0.042). The evidence for 8q24 SNPs with PCa risk in northern Chinese men showed rs16901966, rs1447295 and rs10090154 at 8q24 (region 1, region 2) to be strongly associated with PCa and clinical covariates. The three SNPs at 8q24 could be PCa susceptible genetic markers in northern Chinese men.

Association of Six Susceptibility Loci with Prostate Cancer in Northern Chinese Men

Zhang, Yu-Rong,Xu, Yong,Yang, Kuo,Liu, Ming,Wei, Dong,Zhang, Yao-Guang,Shi, Xiao-Hong,Wang, Jian-Ye,Yang, Fan,Wang, Xin,Liang, Si-Ying,Zhao, Cheng-Xiao,Wang, Fei,Chen, Xin,Sun, Liang,Zhu, Xiao-Quan,Zh Asian Pacific Journal of Cancer Prevention 2012 Asian Pacific journal of cancer prevention Vol.13 No.12

Background/Aim: Six prostate cancer (PCa) susceptibility loci were identified in a genome-wide association study (GWAS) in populations of European decent. However, the associations of these 6 single-nucleotide polymorphisms (SNPs) with PCa has remained tobe clarified in men in Northern China. This study aimed to explore the loci associated with PCa risk in a Northern Chinese population. Methods: Blood samples and clinical information of 289 PCa patients and 288 controls from Beijing and Tianjin were collected. All risk SNPs were genotyped using polymerase chain reaction (PCR)-high resolution melting curve technology and gene sequencing. Associations between PCa and clinical covariates (age at diagnosis, prostate-specific antigen [PSA], Gleason score, tumor stage, and level of aggressiveness) and frequencies of alleles and genotypes of these SNPs were analyzed using genetic statistics. Results: Among the candidate SNPs, 11p15 (rs7127900, A) was associated with PCa risk (P = 0.02, odds ratio [OR] = 1.64, 95% confidence interval [CI] = 1.09-2.46). Genotypes showed differences between cases and controls on 11p15 (rs7127900, A), 11q13 (rs7931342, T), and HNF1B (rs4430796, A) (P = 0.03, P = 0.01, and P = 0.04, respectively). The genotype TG on 11q13 (rs7931342, T) was positively associated with an increased Gleason score (P = 0.04, OR = 2.15, 95% CI = 1.02-4.55). Patients carrying TG on 17q24 (rs1859962, G) were negatively associated with an increased body mass index (BMI) (P = 0.03, OR = 0.44, 95% CI = 0.21-0.92) while those with AG on HNF1B (rs4430796, A) were more likely to have PSA increase (P = 0.002). Conclusion: Our study suggests that 11p15 (rs7127900, A) could be a susceptibility locus associated with PCa in Northern Chinese. Genotype TG on 11q13 (rs7931342, T) could be related to an increased Gleason score, AG on HNF1B (rs4430796, A) could be associated with PSA increase, and TG on 17q24 (rs1859962, G) could be negatively associated with an increased BMI in Chinese men with PCa.

A Fast Gamma-Ray Dose Rate Assessment Method for Complex Geometries Based on Stylized Model Reconstruction

Li-qun Yang,Yong-kuo Liu,Min-jun Peng,Meng-kun Li,Nan Chao 한국원자력학회 2019 Nuclear Engineering and Technology Vol.51 No.5

A fast gamma-ray dose rate assessment method for complex geometries based on stylized modelreconstruction and point-kernel method is proposed in this paper. The complex three-dimensional (3D)geometries are imported as a 3DS format file from 3dsMax software with material and radiometric attributes. Based on 3D stylized model reconstruction of solid mesh, the 3D-geometrical solids are automaticallyconverted into stylized models. In point-kernel calculation, the stylized source models aredivided into point kernels and the mean free paths (mfp) are calculated by the intersections betweenshield stylized models and tracing ray. Compared with MCNP, the proposed method can implementcomplex 3D geometries visually, and the dose rate calculation is accurate and fast.

Susceptibility Loci Associations with Prostate Cancer Risk in Northern Chinese Men

Wang, Na-Na,Xu, Yong,Yang, Kuo,Wei, Dong,Zhang, Yao-Guang,Liu, Ming,Shi, Xiao-Hong,Liang, Si-Ying,Sun, Liang,Zhu, Xiao-Quan,Yang, Yi-Ge,Tang, Lei,Zhao, Cheng-Xiao,Wang, Xin,Chen, Xin,Hui, Juan,Zhang, Asian Pacific Journal of Cancer Prevention 2013 Asian Pacific journal of cancer prevention Vol.14 No.5

Background: KLK3 gene products, like human prostate-specific antigen (PSA), are important biomarkers in the clinical diagnosis of prostate cancer (PCa). G protein-coupled receptor RFX6, C2orf43 and FOXP4 signaling plays important roles in the development of PCa. However, associations of these genes with PCa in northern Chinese men remain to be detailed. This study aimed to investigate their impact on occurrence and level of malignancy. Methods: All subjects were from Beijing and Tianjin, including 266 cases with prostate cancer and 288 normal individuals as controls. We evaluated associations between clinical covariates (age at diagnosis, prostate specific antigen, Gleason score, tumor stage and aggressive) and 6 candidate PCa risk loci, genotyped by PCR- high resolution melting curve and sequencing methods. Results: Case-control analysis of allelic frequency of PCa associated with PCa showed that one of the 6 candidate risk loci, rs339331 in the RFX6 gene, was associated with reduced risk of prostate cancer (odds ratio (OR) = 0.73, 95% confidence interval (CI) =0.57-0.94, P = 0.013) in northern Chinese men. In addition, subjects with CX (CC+TC) genotypes had a decreased risk for prostrate cancer compared to those carrying the TT homozygote (OR =0.64, 95% CI = 0.45- 0.90, P = 0.008). The TT genotype of 13q22 (rs9600079, T) was associated with tumor stage (P=0.044, OR=2.34, 95% CI=0.94-5.87). Other SNPs were not significantly associated with clinical covariates in prostate cancer (P > 0.05). Conclusions. rs339331 in the RFX6 gene may be associated with prostate cancer as a susceptibility locus in northern Chinese men.

Lymphangiogenic and Angiogenic Microvessel Density in Chinese Patients with Gastric Carcinoma: Correlation with Clinicopathologic Parameters and Prognosis

Cao, Fang,Hu, Yong-Wei,Li, Ping,Liu, Ying,Wang, Kuo,Ma, Lei,Li, Peng-Fei,Ni, Can-Rong,Ding, Hou-Zhong Asian Pacific Journal of Cancer Prevention 2013 Asian Pacific journal of cancer prevention Vol.14 No.8

The incidence of gastric cancer worldwide, and in particular in developing countries, has shown a marked increase. Poor prognosis of gastric cancer patients occurs due to the rapid metastasis of the disease via the lymphatic and blood vessels. The aim of this study was to investigate the expression and the clinical significance of D2-40 and CD34 in human gastric cancer. D2-40 and CD34 expression wasdetected in 1,072 cases of Chinese patients with gastric carcinoma using immunohistochemistry. The lymphatic vessel density (LVD) and microvessel density (MVD) were calculated and analyzed and the correlation with the clinicopathological factors and prognosis was determined. The LVD and MVD of the gastric cancer cases were significantly higher compared to those of normal tissues (P < 0.05). The expression of D2-40-LVD and CD34-MVD in the malignancies were positively related to the age, tumor size, invasion depth, lymphatic metastasis and pathological tumor-node-metastasis (pTNM) (P < 0.05); However, no statistically significant difference was identified between them with the patient gender (P > 0.05). Up-regulation of D2-40 and CD34 expression was significantly correlated with the poor survival rate in univariate and multivariate analyses. The LVD marked by D2-40 and the MVD marked by CD34 were positively correlated to the clinicopathological factors of the malignancies and may play important role in the development and progression of gastric cancer.

8q24 rs4242382 Polymorphism is a Risk Factor for Prostate Cancer among Multi-Ethnic Populations: Evidence from Clinical Detection in China and a Meta-analysis

Zhao, Cheng-Xiao,Liu, Ming,Xu, Yong,Yang, Kuo,Wei, Dong,Shi, Xiao-Hong,Yang, Fan,Zhang, Yao-Guang,Wang, Xin,Liang, Si-Ying,Zhao, Fan,Zhang, Yu-Rong,Wang, Na-Na,Chen, Xin,Sun, Liang,Zhu, Xiao-Quan,Yuan Asian Pacific Journal of Cancer Prevention 2014 Asian Pacific journal of cancer prevention Vol.15 No.19

Background: Evidence supporting an association between the 8q24 rs4242382-A polymorphism and prostate cancer (PCa) risk has been reported in North American and Europe populations, though data from Asian populations remain limited. We therefore investigated this association by clinical detection in China, and meta-analysis in Asian, Caucasian and African-American populations. Materials and Methods: Blood samples and clinical information were collected from ethnically Chinese men from Northern China with histologically-confirmed PCa (n=335) and from age-matched normal controls (n=347). The 8q24 (rs4242382) gene polymorphism was genotyped by polymerase chain reaction-high-resolution melting analysis. We initially analyzed the associations between the risk allele and PCa and clinical covariates. A meta-analysis was then performed using genotyping data from a total of 1,793 PCa cases and 1,864 controls from our study and previously published studies in American and European populations, to determine the association between PCa and risk genotype. Results: The incidence of the risk allele was higher in PCa cases than controls (0.222 vs 0.140, $P=7.3{\times}10^{-5}$), suggesting that the 8q24 rs4242382-A polymorphism was associated with PCa risk in Chinese men. The genotypes in subjects were in accordance with a dominant genetic model (ORadj=2.03, 95%CI: 1.42-2.91, $Padj=1.1{\times}10^{-4}$). Presence of the risk allele rs4242382-A at 8q24 was also associated with clinical covariates including age at diagnosis ${\geq}65$ years, prostate specific antigen >10 ng/ml, Gleason score <8, tumor stage and aggressive PCa, compared with the non-risk genotype ($P=4.6{\times}10^{-5}-3.0{\times}10^{-2}$). Meta-analysis confirmed the association between 8q24 rs4242382-A polymorphism and PCa risk (OR=1.62, 95%CI: 1.39-1.88, $P=1.0{\times}10^{-5}$) across Asian, Caucasian and African American populations. Conclusions: The replicated data suggest that the 8q24 rs4242382-A variation might be associated with increased PCa susceptibility in Asian, Caucasian and African American populations. These results imply that this polymorphism may be a useful risk biomarker for PCa in multi-ethnic populations.