Zhen Chen

Prof. Zhen Chen

Shanghai Jiaotong University
orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 August 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
Zhen ChenZhen Chen
Zhen Chen
Tangbin XiaTangbin Xia
Tangbin Xia
Di ZhouDi Zhou
Di Zhou
EPErshun Pan
Ershun Pan
The actual health state of a system is difficult to measure in online applications. Hence, features extracted from the sensor data are usually fused as a composite health index (HI) to represent the system status. If the HI shows explicit increasing or decreasing trend, prognostic methods are applied to extrapolate the future degradation and predict the remaining useful life (RUL). However, the practical requirements of prognostics for HI construction are often not considered. Thus, the advanced index may not capture the fault progression well, which would lead to inaccurate predictions. In this article, an HI construction frame-work based on feature fusion and constrained optimization is proposed. Multiple features are fused with weighted sum and nonlinear fusion functions. Three desired properties of HI for prognostics are considered to build an optimization model of feature weights. To solve this multi-variable model effectively, a self-adaptive differential evolution (SADE) algorithm is proposed. Then, a state-space model based on Wiener process is applied to the constructed HIs for online RUL prediction. To evaluate the performance of the HIs, a consistency-based metric is developed. Illustrative examples using two industrial datasets demonstrate the efficiency and adaptability of the proposed methods.

2 August 2022 in IEEE Transactions on Reliability
Verified
Journal Article
Closed access
Zhen ChenZhen Chen
Zhen Chen
Di ZhouDi Zhou
Di Zhou
Enrico ZioEnrico Zio
Enrico Zio
Tangbin XiaTangbin Xia
Tangbin Xia
Ershun PanErshun Pan
Ershun Pan
Variation of scales or aspect ratios has been one of the main challenges for tracking. To overcome this challenge, most existing methods adopt either multi-scale search or anchor-based schemes, which use a predefined search space in a handcrafted way and therefore limit their performance in complicated scenes. To address this problem, recent anchor-free based trackers have been proposed without using prior scale or anchor information. However, an inconsistency problem between classification and regression degrades the tracking performance. To address the above issues, we propose a simple yet effective tracker (named Siamese Box Adaptive Network, SiamBAN) to learn a target-aware scale handling schema in a data-driven manner. Our basic idea is to predict the target boxes in a per-pixel fashion through a fully convolutional network, which is anchor-free. Specifically, SiamBAN divides the tracking problem into classification and regression tasks, which directly predict objectiveness and regress bounding boxes, respectively. A no-prior box design is proposed to avoid tuning hyper-parameters related to candidate boxes, which makes SiamBAN more flexible. SiamBAN further uses a target-aware branch to address the inconsistency problem. Experiments on benchmarks including VOT2018, VOT2019, OTB100, UAV123, LaSOT and TrackingNet show that SiamBAN achieves promising performance and runs at 35 FPS.

13 December 2019 in IEEE Transactions on Reliability
Verified
Journal Article
Closed access
Zhen ChenZhen Chen
Zhen Chen
Tangbin XiaTangbin Xia
Tangbin Xia
YLYanting Li
Yanting Li
Ershun PanErshun Pan
Ershun Pan
Degradation modeling is an important method of reliability analysis for highly reliable products. The common degradation models are based on specific stochastic processes. This limits the widespread application of the modeling methods. A unified approach toward general degradation models is lacked. To address this issue, this article uses Tweedie exponential dispersion processes (TEDP) to establish degradation models. In such a way, the common stochastic processes turn out to be the special cases of TEDP. Then, the TEDP models can provide us more suitable models to describe the degradation paths and thereby improve the accuracy of reliability analysis. To develop the mathematical tractability of TEDP, we use the saddle-point approximation method to approximate the probability density function. Considering the unit-to-unit variability and imperfect observation, the TEDP model incorporated random effects and measurement errors are discussed. To illustrate the applicability and advantages of the TEDP models, we propose a Bayesian framework for the prognostic. A component-wise Metropolis–Hastings algorithm is developed to update the distributions of remaining useful life. Additionally, we also construct an optimization model under the constraint of budget for the accelerated degradation test planning by using TEDP. Finally, two case studies are presented to illustrate the proposed methods.

9 September 2021 in IEEE Transactions on Reliability
Verified
Journal Article
Closed access
Zhen ChenZhen Chen
Zhen Chen
Tangbin XiaTangbin Xia
Tangbin Xia
YLYaping Li
Yaping Li
Ershun PanErshun Pan
Ershun Pan
The degradation data of highly reliable products are usually analyzed by stochastic process models, such as Wiener process, gamma process and inverse Gaussian process models. If such a specific degradation model is wrongly assumed, then poor analysis results of reliability assessment would be obtained. Therefore, a class of exponential-dispersion processes, named Tweedie exponential-dispersion process (TEDP), is proposed to describe the products’ degradation paths. The TEDP model which comprises the aforementioned stochastic processes as its special cases, is more flexible and applicable for degradation modeling. Considering the nonlinear characteristics of degradation paths and the unit-to-unit variability among the product units, random-effect models are established based on the nonlinear TEDP models with random drift and dispersion parameters. To improve the mathematical tractability of these models, the variational inference, expectation maximization algorithm and differential evolution algorithm are used to estimate the unknown model parameters. Furthermore, two nonlinear TEDP models with accelerated factors and random effects are developed for accelerated degradation analysis. Finally, a simulation study and three real applications are presented to show the effectiveness and superiority of the proposed models and methods.

6 February 2025 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
YHYue Huang
Yue Huang
Zhen ChenZhen Chen
Zhen Chen
ZCZhaoxiang Chen
Zhaoxiang Chen
DZDi Zhou
Di Zhou
EPErshun Pan
Ershun Pan

10 October 2023 in Journal of Manufacturing Systems
Verified
Journal Article
Closed access
ZCZhaoxiang Chen
Zhaoxiang Chen
Zhen ChenZhen Chen
Zhen Chen
DZDi Zhou
Di Zhou
Tangbin XiaTangbin Xia
Tangbin Xia
EPErshun Pan
Ershun Pan