PSAM 16 - Session M12 Overview

PSAM 16 Conference Session M12 Overview

Session Chair: Dusko Kancev (dkancev@kkg.ch)

Paper 1 VI320

Lead Author: Vivek Agarwal Co-author(s): Vaibhav Yadav, Andrei V. Gribok, Matthew Yarlett, and Brad Diggans

Preventive Maintenance Optimization based on Historical Data
Nuclear power plants (NPPs) follow an established maintenance plan to ensure safe and reliable plant operation. These established maintenance plans are part of a preventive maintenance (PM) strategy and are defined for all equipment and systems at a plant site. For the time-based PM tasks, workers from electrical, mechanical, and instrumentation and controls maintenance perform different activities, like inspection, calibration, replacement, and refurbishment, at a defined interval, usually without taking into consideration the condition of the equipment and system. Due to the high cost and labor-intensive nature of the PM strategy, it is important to optimize these intervals through PM Optimization (PMO). In this presentation, we will use historic data for a motor-driven pump is used to evaluate any change in the risk of failure of a system or component if these PM interval are revised. The presentation will also discuss potential cost savings with the recommended change in interval and minimal to no risk of failure of the system.

Preventive Maintenance Optimization based on Historical Data

Nuclear power plants (NPPs) follow an established maintenance plan to ensure safe and reliable plant operation. These established maintenance plans are part of a preventive maintenance (PM) strategy and are defined for all equipment and systems at a plant site. For the time-based PM tasks, workers from electrical, mechanical, and instrumentation and controls maintenance perform different activities, like inspection, calibration, replacement, and refurbishment, at a defined interval, usually without taking into consideration the condition of the equipment and system. Due to the high cost and labor-intensive nature of the PM strategy, it is important to optimize these intervals through PM Optimization (PMO). In this presentation, we will use historic data for a motor-driven pump is used to evaluate any change in the risk of failure of a system or component if these PM interval are revised. The presentation will also discuss potential cost savings with the recommended change in interval and minimal to no risk of failure of the system.

Paper VI320 | |

Name: Vivek Agarwal (vivek.agarwal@inl.gov)

Bio: Dr. Vivek Agarwal is a Senior Research Scientist and Technical Lead of the Fission Battery Initiative. He specializes in crosscutting applications and advancement of inter-disciplinary research to enable resilient real-time measurement and control of process variables within the nuclear and other critical industries. Dr. Agarwal received a Bachelor of Engineering in electrical engineering from University of Madras, India in 2001, M.S. in electrical engineering from University of Tennessee, Knoxville in 2005, and Ph.D. in nuclear engineering from Purdue University in 2011. He joined INL as a research in 2011 and since then has lead projects under multiple DOE programs such as Light Water Research Sustainability, Nuclear Energy Enabling Technologies – Advanced Sensors and Instrumentation Program, Technology Transition Office, and others. Dr. Agarwal was awarded 2019 Presidential Early Career Awards for Scientists and Engineers, and 2016 Laboratory Director Early Career Achievement Award.

Country: USA
Company: Idaho National Laboratory
Job Title: Senior Research Scientist

Paper 2 SY189

Lead Author: Sylwia WERBIŃSKA-WOJCIECHOWSKA Co-author(s): AGNIESZKA TUBIS, agnieszka.tubis@pwr.edu.pl KLAUDIA WINIARSKA, klaudia.winiarska@pwr.edu.pl HONORATA POTURAJ, honorata.poturaj@pwr.edu.pl

Risk Of Maintenance Resource Sharing In Transport Systems
The authors investigate the problem of maintenance resource sharing for transport systems in the context of operational risk assessment. The paper includes a short introduction to the maintenance problems and a discussion of maintenance resource sharing issues in transport systems' effective performance. Later, a three-parameter risk assessment ratio is introduced. It includes a probability of disruption occurrence, consequences of disruption occurrence, and a new measure characterizing maintenance resources availability. Later, the problem of maintenance resources availability is analyzed and discussed. Finally, a short case study is introduced. The presented paper gives the possibility to identify research gaps and possible future research directions connected with optimization of maintenance problems in transportation organizations.

Risk Of Maintenance Resource Sharing In Transport Systems

The authors investigate the problem of maintenance resource sharing for transport systems in the context of operational risk assessment. The paper includes a short introduction to the maintenance problems and a discussion of maintenance resource sharing issues in transport systems' effective performance. Later, a three-parameter risk assessment ratio is introduced. It includes a probability of disruption occurrence, consequences of disruption occurrence, and a new measure characterizing maintenance resources availability. Later, the problem of maintenance resources availability is analyzed and discussed. Finally, a short case study is introduced. The presented paper gives the possibility to identify research gaps and possible future research directions connected with optimization of maintenance problems in transportation organizations.

Paper SY189 | Download the paper file. | Download the presentation pdf file.

Name: Sylwia WERBIŃSKA-WOJCIECHOWSKA (sylwia.werbinska@pwr.edu.pl)

Bio: Sylwia Werbinska-Wojciechowska is an Associate Professor at the Faculty of Mechanical Engineering, Department of Operation and Maintenance of Technical Systems at Wroclaw University of Science and Technology, Poland. Her field of current interests is related to the issues of technical systems maintenance modelling, physical asset management, modelling and performance measurement of transport systems operation, as well as supply chains resilience and vulnerability problems. She is a Member of Polish Logistics Association and Polish Maintenance Society. She represents the Wroclaw University of Science and Technology in European Safety, Reliability and Data Association and European Safety and Reliability Association-ESRA. She is a Member of ESRA’s Technical Committee: Maintenance Modelling and Applications. She was a leader or a performer in 14 national or international research projects in the fields of technical systems maintenance modelling, reliability and safety identific

Country: POL
Company: Wroclaw University of Science and Technology
Job Title: Assoc. Professor

Paper 3 TA24

Lead Author: Tamer Tevetoglu Co-author(s): Bernd Bertsche bernd.bertsche@ima.uni-stuttgart.de

A Machine Learning Approach to Enhance the Information on Suspensions in Life Data Analysis
Increasing digitalization and implementation of sensors in systems result in high data availability, which enables and benefits data-driven approaches. Commonly, these approaches revolve around predictive maintenance, anomaly detection, or clustering. In this paper, we analyze the practicality and performance of life data analyses based on neural networks. To this end, the Weibull analysis is extended with a machine learning approach and compared with conventional approaches in a laboratory test setup. Reliability engineers usually have budget and time constraints regarding testing strategies. These constraints manifest as an inability to accurately verify a system’s reliability with a pre-defined confidence due to small sample sizes, insufficient number of failures from testing, or inadequate choice of life data analysis methods. Conventional approaches in life data analysis counteract these constraints by taking suspensions into account or allowing to correct the bias when computing parameter estimates and confidence bounds. Hence, engineers only have limited number of tools in order to deal with constraints in reliability testing. Previous studies have shown that these counteracting measures may not be effective under certain circumstances, i.e. despite taking suspensions into account or using bias-corrections, parameter estimates may differ substantially from the ground truth. This may lead to a false sense of security regarding the operational life of a product. As data-driven approaches become steadily more important in other reliability engineering areas, e.g. Prognostics and Health Management (PHM), the focus of this paper lies on the analysis whether some shortcomings in life data analysis can be mitigated by using data-driven approaches in addition to or instead of conventional approaches. We develop a data-driven model that uses a neural network to recognize patterns in sequences of data, e.g. numerical times series data emanating from sensors. A trained model is able to output the remaining useful lifetime (RUL) of a system based on sequential sensor data like temperature, vibration, etc. In life data analysis, failures and their respective sensor data can be used to train data-driven model. This trained model is then being used to predict the RUL of the suspensions. If the predicted failure times are close to the unknown real failure times of the suspensions, one may use the predicted failures in addition to the actual failures, and thus may obtain more accurate parameter estimates and confidence bounds. In order to verify this proposition, we conduct a study to determine how using neural networks to increase the number of failures by predicting the RULs of suspensions actually performs against conventional approaches like bias-corrections. For this purpose, we use a turbofan engine data set from NASA and compare the performances of three Weibull analysis approaches to each other: 1. Maximum likelihood estimation (MLE) with bias-correction 2. MLE with machine learning 3. MLE with machine learning and bias-correction For each approach, parameter estimates and confidence bounds are evaluated for a censored subset of the data set with varying sample sizes and censoring shares. The first approach is based on the MLE in combination with the Hirose and Ross bias-correction. This bias-correction method performed best in a previous study. The second approach requires training a machine learning model with actual failures and subsequent prediction of the suspensions’ RULs. Then a conventional Weibull analysis is conducted with the actual and predicted failures. The third approach includes a subsequent bias-correction after using the machine learning model. Based on this simulation study, this paper’s main objective is to conclude on whether the use of neural networks can mitigate above mentioned shortcomings, and if so, what the precise prerequisites are. These prerequisites include the sample size, number of failures, number of suspensions, censoring share, and choice of methods. Our special attention lies on the minimum number of actual failures during testing that are needed in order to train an adequate data-driven model.

A Machine Learning Approach to Enhance the Information on Suspensions in Life Data Analysis

Increasing digitalization and implementation of sensors in systems result in high data availability, which enables and benefits data-driven approaches. Commonly, these approaches revolve around predictive maintenance, anomaly detection, or clustering. In this paper, we analyze the practicality and performance of life data analyses based on neural networks. To this end, the Weibull analysis is extended with a machine learning approach and compared with conventional approaches in a laboratory test setup. Reliability engineers usually have budget and time constraints regarding testing strategies. These constraints manifest as an inability to accurately verify a system’s reliability with a pre-defined confidence due to small sample sizes, insufficient number of failures from testing, or inadequate choice of life data analysis methods. Conventional approaches in life data analysis counteract these constraints by taking suspensions into account or allowing to correct the bias when computing parameter estimates and confidence bounds. Hence, engineers only have limited number of tools in order to deal with constraints in reliability testing. Previous studies have shown that these counteracting measures may not be effective under certain circumstances, i.e. despite taking suspensions into account or using bias-corrections, parameter estimates may differ substantially from the ground truth. This may lead to a false sense of security regarding the operational life of a product. As data-driven approaches become steadily more important in other reliability engineering areas, e.g. Prognostics and Health Management (PHM), the focus of this paper lies on the analysis whether some shortcomings in life data analysis can be mitigated by using data-driven approaches in addition to or instead of conventional approaches. We develop a data-driven model that uses a neural network to recognize patterns in sequences of data, e.g. numerical times series data emanating from sensors. A trained model is able to output the remaining useful lifetime (RUL) of a system based on sequential sensor data like temperature, vibration, etc. In life data analysis, failures and their respective sensor data can be used to train data-driven model. This trained model is then being used to predict the RUL of the suspensions. If the predicted failure times are close to the unknown real failure times of the suspensions, one may use the predicted failures in addition to the actual failures, and thus may obtain more accurate parameter estimates and confidence bounds. In order to verify this proposition, we conduct a study to determine how using neural networks to increase the number of failures by predicting the RULs of suspensions actually performs against conventional approaches like bias-corrections. For this purpose, we use a turbofan engine data set from NASA and compare the performances of three Weibull analysis approaches to each other: 1. Maximum likelihood estimation (MLE) with bias-correction 2. MLE with machine learning 3. MLE with machine learning and bias-correction For each approach, parameter estimates and confidence bounds are evaluated for a censored subset of the data set with varying sample sizes and censoring shares. The first approach is based on the MLE in combination with the Hirose and Ross bias-correction. This bias-correction method performed best in a previous study. The second approach requires training a machine learning model with actual failures and subsequent prediction of the suspensions’ RULs. Then a conventional Weibull analysis is conducted with the actual and predicted failures. The third approach includes a subsequent bias-correction after using the machine learning model. Based on this simulation study, this paper’s main objective is to conclude on whether the use of neural networks can mitigate above mentioned shortcomings, and if so, what the precise prerequisites are. These prerequisites include the sample size, number of failures, number of suspensions, censoring share, and choice of methods. Our special attention lies on the minimum number of actual failures during testing that are needed in order to train an adequate data-driven model.

Paper TA24 | Download the paper file. | Download the presentation pdf file. Download the presentation PowerPoint file.

Name: Tamer Tevetoglu (tamer.tevetoglu@ima.uni-stuttgart.de)

Bio: Tamer Tevetoglu studied Mechanical Engineering at the University of Stuttgart in Germany and received his academic degree Master of Science in 2017. Since 2017, he is a researcher in the Reliability Engineering Department at the Institute of Machine Components at the University of Stuttgart and pursues his PhD studies.

Country: DEU
Company: University of Stuttgart
Job Title: PhD Student