Fresh new look for system-level prognostics

Model-based prognostic approaches use first-principle or regression models to estimate and predict the system’s health state in order to determine the remaining useful life (RUL). Then, in order to handle the prediction results uncertainty, the Bayesian framework is usually used, in which the prior estimates are updated by infield measurements without changing the model parameters. Nevertheless, in the case of system-level prognostic, the mere updating of the prior estimates, based on a predetermined model, is no longer sufficient. This is due to the mutual interactions between components that increase the system modeling uncertainties and may lead to an inaccurate prediction of the system RUL (SRUL). Therefore, this paper proposes a new methodology for online joint uncertainty quantification and model estimation based on particle filtering (PF) and gradient descent (GD). In detail, the inoperability input-output model (IIM) is used to characterize system degradations considering interactions between components and effects of the mission profile; and then the inoperability of system components is estimated in a probabilistic manner using PF. In the case of consecutive discrepancy between the prior and posterior estimates of the system health state, GD is used to correct and to adapt the IIM parameters. To illustrate the effectiveness of the proposed methodology and its suitability for an online implementation, the Tennessee Eastman Process is investigated as a case study.

Download Full-text

Integration of System-Level Design and Detailed Design Models of Mechatronic Systems Based on SysML and Step AP 203 Standard

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.249-250.1160 ◽

2012 ◽

Vol 249-250 ◽

pp. 1160-1165

Author(s):

Yu Sheng Liu ◽

Hong Ri Fan

Keyword(s):

System Modeling ◽

Automatic Generation ◽

Transformation Method ◽

System Level ◽

Mechatronic System ◽

Mechatronic Systems ◽

Pendulum System ◽

Modeling Technology ◽

Inverted Pendulum System

In this study, a meta-model based method is proposed for automatic generation of STEP AP 203 file for mechanical part of the mechatronic system from the SysML model. System modeling technology in SysML is firstly presented and then the model of EXPRESS language is employed to transfer the information from SysML through the model transformation method. Based on the information parsed from the resulting EXPRESS model, the STEP file is finally generated by creating the B_REP model in STEP AP 203 standard. The proposed method is illustrated with a case study named as inverted pendulum system (IPS).

Download Full-text

Integrated Real-Time Event Based Cost Modeling of Battery Manufacturing System

Volume 1: Materials; Micro and Nano Technologies; Properties, Applications and Systems; Sustainable Manufacturing ◽

10.1115/msec2014-3917 ◽

2014 ◽

Author(s):

Yang Li ◽

Qing Chang

Keyword(s):

Real Time ◽

Manufacturing System ◽

System Modeling ◽

Integrated System ◽

Cost Modeling ◽

System Level ◽

System Level Modeling ◽

Event Based ◽

Unified Index

Information of battery manufacturing system is becoming increasingly transparent, detailed and real-time. Despite the big potential in improving productivity, the advantages of information are not fully realized due to a lack of system level modeling. Motivated by this need, we develop an integrated system modeling approach to quantify the systematic impact of stations and supporting activities with a unified index called event based cost (EBC). The analysis provides a severity ranking of stations and supporting activities. A case study is conducted to demonstrate the application of the model in a battery production system and its ability to facilitate decision making.

Download Full-text

Fault Diagnosis and Prognosis Based on Deep Belief Network and Particle Filtering

Annual Conference of the PHM Society ◽

10.36001/phmconf.2018.v10i1.540 ◽

2018 ◽

Vol 10 (1) ◽

Author(s):

Guangxing Niu ◽

Shije Tang ◽

Zhichao Liu ◽

Guangquan Zhao ◽

Bin Zhang

Keyword(s):

Deep Learning ◽

Fault Diagnosis ◽

Particle Filtering ◽

Learning Algorithms ◽

Remaining Useful Life ◽

Health State ◽

Diagnosis And Prognosis ◽

Fault Dynamics ◽

Useful Life ◽

Fault Diagnosis And Prognosis

Fault diagnosis and prognosis (FDP) plays more and more important role in industries FDP aims to estimate current fault condition and then predict the remaining useful life (RUL). Based on the estimation of health state and RUL, essential decisions on maintenance, control, and planning can be conducted optimally in terms of economy, efficiency, and availability. With the increase of system complexity, it becomes more and more difficult to model the fault dynamics, especially for multiple interacting fault modes and for fault modes that are affected by many internal and external factors. With the development of machine learning and big data, deep learning algorithms become important tools in FDP due to their excellent performance in data processing, information extraction, and automatic modeling. In the past a few years, deep learning algorithms demonstrate outstanding performance in feature extraction and learning fault dynamics. As emerging techniques, their powerful learning capabilities attract more and more attentions and have been extended to various applications. This work presents a novel diagnosis and prognosis methodology which combined deep belief networks (DBNs) and Bayesian estimation. In the proposed work, the DBNs are trained offline using available historical data. The fault dynamic model is then represented by the trained DBNs and modeling uncertainty is described by noise. The integration of DBNs with particle filtering is then developed to provide an estimation of the current fault state and predict the remaining useful life, which is very suitable and efficient for most nonlinear fault models. Experimental studies of lithium-ion batteries are presented to verify the effectiveness of the proposed solution.

Download Full-text

Evaluating The Effectiveness Of Problem-Based Learning (Pbl) Implemented In The Textile Engineering Course - A Case Study On Ahsanullah University Of Science And Technology, Bangladesh

Balkan Region Conference on Engineering and Business Education ◽

10.2478/cplbu-2014-0024 ◽

2014 ◽

Vol 1 (1) ◽

pp. 111-114

Author(s):

Lal Mohan Baral ◽

Ramzan Muhammad ◽

Claudiu Vasile Kifor ◽

Ioan Bondrea

Keyword(s):

Engineering Students ◽

Science And Technology ◽

Problem Based Learning ◽

Professional Life ◽

System Level ◽

Teaching Tool ◽

Technical Problems ◽

Empirical Survey ◽

Undergraduate Programs

AbstractProblem-based learning as a teaching tool is now used globally in many areas of higher education. It provides an opportunity for students to explore technical problems from a system-level perspective and to be self-directed life-long learner which is mandatory for equipping engineering students with the skill and knowledge. This paper presents a case study illustrating the effectiveness of implemented Problem-based learning (PBL) during five semesters in the undergraduate programs of Textile Engineering in Ahsanullah University of Science and Technology (AUST). An assessment has been done on the basis of feedback from the students as well as their employers by conducting an empirical survey for the evaluation of PBL impact to enhance the student's competencies. The Evaluations indicate that students have achieved remarkable competencies through PBL practices which helped them to be competent in their professional life.

Download Full-text

A Methodology for Characterizing System-Level ESD Sensitivity

ISTFA 2004: Conference Proceedings from the 30th International Symposium for Testing and Failure Analysis ◽

10.31399/asm.cp.istfa2004p0277 ◽

2004 ◽

Author(s):

Marie-Pascale Chagny ◽

John A. Naoum

Keyword(s):

Electrostatic Discharge ◽

Computer Systems ◽

Electronic Equipment ◽

Experimental Methodology ◽

Computer Users ◽

System Level ◽

Permanent Damage ◽

Design Improvement ◽

Desktop Computers

Abstract Over the years, failures induced by an electrostatic discharge (ESD) have become a major concern for semiconductor manufacturers and electronic equipment makers. The ESD events that cause destructive failures have been studied extensively [1, 2]. However, not all ESD events cause permanent damage. Some events lead to recoverable failures that disrupt system functionality only temporarily (e.g. reboot, lockup, and loss of data). These recoverable failures are not as well understood as the ones causing permanent damage and tend to be ignored in the ESD literature [3, 4]. This paper analyzes and characterizes how these recoverable failures affect computer systems. An experimental methodology is developed to characterize the sensitivity of motherboards to ESD by simulating the systemlevel ESD events induced by computer users. The manuscript presents a case study where this methodology was used to evaluate the robustness of desktop computers to ESD. The method helped isolate several weak nets contributing to the failures and identified a design improvement. The result was that the robustness of the systems improved by a factor of 2.

Download Full-text

Hybrid remaining useful life prediction method. A case study on railway D-cables

Reliability Engineering & System Safety ◽

10.1016/j.ress.2021.107746 ◽

2021 ◽

pp. 107746

Author(s):

Yu Zang ◽

Wei Shangguan ◽

Baigen Cai ◽

Huasheng Wang ◽

Michael. G. Pecht

Keyword(s):

Life Prediction ◽

Prediction Method ◽

Remaining Useful Life ◽

Useful Life

Download Full-text

Health State Estimation and Remaining Useful Life Prediction of Power Devices Subject to Noisy and Aperiodic Condition Monitoring

IEEE Transactions on Instrumentation and Measurement ◽

10.1109/tim.2021.3054429 ◽

2021 ◽

Vol 70 ◽

pp. 1-16

Author(s):

Shuai Zhao ◽

Yingzhou Peng ◽

Fei Yang ◽

Enes Ugur ◽

Bilal Akin ◽

...

Keyword(s):

State Estimation ◽

Condition Monitoring ◽

Life Prediction ◽

Remaining Useful Life ◽

Health State ◽

Power Devices ◽

Useful Life

Download Full-text

Particle Filtering Based Remaining Useful Life Prediction for Electromagnetic Coil Insulation

Sensors ◽

10.3390/s21020473 ◽

2021 ◽

Vol 21 (2) ◽

pp. 473

Author(s):

Haifeng Guo ◽

Aidong Xu ◽

Kai Wang ◽

Yue Sun ◽

Xiaojia Han ◽

...

Keyword(s):

Particle Filtering ◽

Remaining Useful Life ◽

Electrical Parameters ◽

Degradation Model ◽

Accelerated Degradation ◽

Insulation Failure ◽

Electromagnetic Coils ◽

Degradation Monitoring ◽

Insulation Degradation ◽

Useful Life

Electromagnetic coils are one of the key components of many systems. Their insulation failure can have severe effects on the systems in which coils are used. This paper focuses on insulation degradation monitoring and remaining useful life (RUL) prediction of electromagnetic coils. First, insulation degradation characteristics are extracted from coil high-frequency electrical parameters. Second, health indicator is defined based on insulation degradation characteristics to indicate the health degree of coil insulation. Finally, an insulation degradation model is constructed, and coil insulation RUL prediction is performed by particle filtering. Thermal accelerated degradation experiments are performed to validate the RUL prediction performance. The proposed method presents opportunities for predictive maintenance of systems that incorporate coils.

Download Full-text

Predicting Remaining Useful Life of Rolling Bearings Based on Reliable Degradation Indicator and Temporal Convolution Network with the Quantile Regression

Applied Sciences ◽

10.3390/app11114773 ◽

2021 ◽

Vol 11 (11) ◽

pp. 4773

Author(s):

Qiaoping Tian ◽

Honglei Wang

Keyword(s):

Quantile Regression ◽

Probability Density ◽

Degradation Process ◽

Remaining Useful Life ◽

Health State ◽

Rolling Bearings ◽

Data Set ◽

Time Frequency ◽

Useful Life ◽

Degradation Indicator

High precision and multi information prediction results of bearing remaining useful life (RUL) can effectively describe the uncertainty of bearing health state and operation state. Aiming at the problem of feature efficient extraction and RUL prediction during rolling bearings operation degradation process, through data reduction and key features mining analysis, a new feature vector based on time-frequency domain joint feature is found to describe the bearings degradation process more comprehensively. In order to keep the effective information without increasing the scale of neural network, a joint feature compression calculation method based on redefined degradation indicator (DI) was proposed to determine the input data set. By combining the temporal convolution network with the quantile regression (TCNQR) algorithm, the probability density forecasting at any time is achieved based on kernel density estimation (KDE) for the conditional distribution of predicted values. The experimental results show that the proposed method can obtain the point prediction results with smaller errors. Compared with the existing quantile regression of long short-term memory network(LSTMQR), the proposed method can construct more accurate prediction interval and probability density curve, which can effectively quantify the uncertainty of bearing running state.

Download Full-text