Zheng Chang

Overview:

Dr. Chang's research interests include radiation therapy treatment assessment using MR quantitative imaging, image guided radiation therapy (IGRT), fast MR imaging using parallel imaging and strategic phase encoding, and motion management for IGRT.

Positions:

Professor of Radiation Oncology

Radiation Oncology
School of Medicine

Member of the Duke Cancer Institute

Duke Cancer Institute
School of Medicine

Education:

Ph.D. 2006

University of British Columbia (Canada)

Grants:

Publications:

Remaining Useful Lifetime Prediction for the Equipment with the Random Failure Threshold

© 2019 IEEE. Prognostics and health management (PHM) technology is widely used in industrial production, and its core is to predict the remaining useful life (RUL) of the equipment. For the existing research of RUL prediction, the impact of random failure threshold (RFT) has not been analyzed. To solve this problem, an RUL prediction method based on the Kalman filter is proposed. Firstly, a nonlinear Wiener degradation model is built in this paper. Then, the parameters of the degradation model are estimated by the maximum likelihood estimation (MLE) method and the distribution coefficients of RFT are calculated by the expected maximum (EM) algorithm. In addition, the Kalman filtering technique is applied to renewal the degradation states by obtaining condition monitoring (CM) data. Finally, the analytical expression of probability density function (PDF) for the RUL is derived by considering the RFT. The simulation example shows that the method in this paper has advantages of RUL prediction, and thus can have potentially engineering application value.
Authors
Wang, Z; Chen, Y; Cai, Z; Chang, Z; Wang, T
MLA Citation
Wang, Z., et al. “Remaining Useful Lifetime Prediction for the Equipment with the Random Failure Threshold.” 2019 Prognostics and System Health Management Conference, Phm Qingdao 2019, 2019. Scopus, doi:10.1109/PHM-Qingdao46334.2019.8942960.
URI
https://scholars.duke.edu/individual/pub1451119
Source
scopus
Published In
2019 Prognostics and System Health Management Conference, Phm Qingdao 2019
Published Date
DOI
10.1109/PHM-Qingdao46334.2019.8942960

Equipment Maintenance Decision Model Based on Degradation Data and Failure Data

© 2019 IEEE. The degradation of data and failure data is used to make the maintenance decision of equipment in this paper. Firstly, the Wiener process is used to build the degradation model which is according to the degradation data of the equipment. Then, the random distribution coefficient of failure threshold is estimated by the failure data of the equipment, and we also derive the analytical expression of the remaining useful lifetime (RUL) distribution of the equipment. Finally, the maintenance decision model is established according to the renewal-reward theory and RUL prediction data which can achieve optimal maintenance strategy of equipment. The simulation example shows that the method in this paper can prolong the run time cost of equipment and effectively reduce the life cycle which has broad application prospects.
Authors
Wang, ZZ; Chen, YX; Cai, ZY; Xiang, HC; Chang, Z
MLA Citation
Wang, Z. Z., et al. “Equipment Maintenance Decision Model Based on Degradation Data and Failure Data.” Proceedings of 2019 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering, Qr2mse 2019, 2019, pp. 237–42. Scopus, doi:10.1109/QR2MSE46217.2019.9021194.
URI
https://scholars.duke.edu/individual/pub1451118
Source
scopus
Published In
Proceedings of 2019 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering, Qr2mse 2019
Published Date
Start Page
237
End Page
242
DOI
10.1109/QR2MSE46217.2019.9021194

Effectiveness evaluation method of system-of-systems based on operation loop and improved information entropy

© 2019, Editorial Office of Systems Engineering and Electronics. All right reserved. Aiming at the problem of various equipment and complicated correlations in operation system-of-systems under the information conditions, an effectiveness evaluation method of system-of-systems based on the operation loop and improved information entropy is proposed according to the traction of enemy targets. The equipment and correlations are abstracted as nodes and edges. The edges' metrics are determined according to the tactical and technical indexes of the nodes, and the network model of operation system-of-systems based on the operation loop is constructed. The methods to determine the number of the operation loop based on the adjacency matrix and evaluate the effectiveness of the operation loop based on improved information entropy are respectively proposed. The effectiveness evaluation model of operation system-of-systems is built according to the number and effectiveness of the operation loop involved in each target node. Taking an combating large surface warship operation system-of-systems as an example, the results show that the proposed method has fully taken the heterogeneity and uncertainty of each equipment and correlation into consideration to evaluate the effectiveness of the system-of-systems comprehensively and objectively. The proposed method can provide methodological support for the effectiveness evaluation and structural optimization of operation system-of-systems.
Authors
Luo, C; Chen, Y; Wang, L; Wang, Z; Chang, Z
MLA Citation
Luo, C., et al. “Effectiveness evaluation method of system-of-systems based on operation loop and improved information entropy.” Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics, vol. 41, no. 1, Jan. 2019, pp. 73–80. Scopus, doi:10.3969/j.issn.1001-506X.2019.01.11.
URI
https://scholars.duke.edu/individual/pub1451120
Source
scopus
Published In
Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics
Volume
41
Published Date
Start Page
73
End Page
80
DOI
10.3969/j.issn.1001-506X.2019.01.11

Evaluation of Equipment Contribution Rate to System-of-systems Based on Hybrid Parameter Evidential Network

© 2018, Editorial Board of Acta Armamentarii. All right reserved. An evaluation method of equipment contribution rate to system-of-systems based on hybrid parameter evidential network is proposed for the complicated correlation between the capability of equipment system-of-systems and the uncertainty of evaluating information. An evidential network structure model for evaluation of equipment contribution rate to system-of-systems is constructed based on the correlation between the capabilities of the same level. The requirement satisfactory degree evaluation methods for evaluating the capabilities of the same level based on conditional belief parameter model and the cross-level based on belief rule parameter model are proposed, respectively, and an evaluation model of equipment contribution rate to system-of-systems is established according to the utility function. An anti-aircraft carrier equipment system-of-systems is modeled and analyzed.The results show that the proposed method can reflect the emergence of the overall capability of equipment system-of-systems, and can evaluate the equipment contribution rate to system-of-systems comprehensively and objectively.
Authors
Luo, CK; Chen, YX; Zhang, YM; Chang, Z; Zhu, Q
MLA Citation
Luo, C. K., et al. “Evaluation of Equipment Contribution Rate to System-of-systems Based on Hybrid Parameter Evidential Network.” Binggong Xuebao/Acta Armamentarii, vol. 39, no. 12, Dec. 2018, pp. 2488–96. Scopus, doi:10.3969/j.issn.1000-1093.2018.12.023.
URI
https://scholars.duke.edu/individual/pub1451121
Source
scopus
Published In
Binggong Xuebao/Acta Armamentarii
Volume
39
Published Date
Start Page
2488
End Page
2496
DOI
10.3969/j.issn.1000-1093.2018.12.023

An investigation of machine learning methods in delta-radiomics feature analysis.

PURPOSE: This study aimed to investigate the effectiveness of using delta-radiomics to predict overall survival (OS) for patients with recurrent malignant gliomas treated by concurrent stereotactic radiosurgery and bevacizumab, and to investigate the effectiveness of machine learning methods for delta-radiomics feature selection and building classification models. METHODS: The pre-treatment, one-week post-treatment, and two-month post-treatment T1 and T2 fluid-attenuated inversion recovery (FLAIR) MRI were acquired. 61 radiomic features (intensity histogram-based, morphological, and texture features) were extracted from the gross tumor volume in each image. Delta-radiomics were calculated between the pre-treatment and post-treatment features. Univariate Cox regression and 3 multivariate machine learning methods (L1-regularized logistic regression [L1-LR], random forest [RF] or neural networks [NN]) were used to select a reduced number of features, and 7 machine learning methods (L1-LR, L2-LR, RF, NN, kernel support vector machine [KSVM], linear support vector machine [LSVM], or naïve bayes [NB]) was used to build classification models for predicting OS. The performances of the total 21 model combinations built based on single-time-point radiomics (pre-treatment, one-week post-treatment, and two-month post-treatment) and delta-radiomics were evaluated by the area under the receiver operating characteristic curve (AUC). RESULTS: For a small cohort of 12 patients, delta-radiomics resulted in significantly higher AUC than pre-treatment radiomics (p-value<0.01). One-week/two-month delta-features resulted in significantly higher AUC (p-value<0.01) than the one-week/two-month post-treatment features, respectively. 18/21 model combinations were with higher AUC from one-week delta-features than two-month delta-features. With one-week delta-features, RF feature selector + KSVM classifier and RF feature selector + NN classifier showed the highest AUC of 0.889. CONCLUSIONS: The results indicated that delta-features could potentially provide better treatment assessment than single-time-point features. The treatment assessment is substantially affected by the time point for computing the delta-features and the combination of machine learning methods for feature selection and classification.
Authors
MLA Citation
Chang, Yushi, et al. “An investigation of machine learning methods in delta-radiomics feature analysis.Plos One, vol. 14, no. 12, 2019, p. e0226348. Pubmed, doi:10.1371/journal.pone.0226348.
URI
https://scholars.duke.edu/individual/pub1423241
PMID
31834910
Source
pubmed
Published In
Plos One
Volume
14
Published Date
Start Page
e0226348
DOI
10.1371/journal.pone.0226348