Pub Date : 2022-07-12DOI: 10.36001/ijphm.2022.v13i2.3141
C. Walker, Ahmad Y. Al Rashdan, V. Agarwal
As integral components of any power plant, transformers sup-ply the generated electricity to the grid. However, the trans-former’s cellulose-based paper insulation and the mineral oilin which it is immersed break down over time under stan-dard operating conditions—or more rapidly due to potentialfaults within the system. This technical brief exhibits a col-lection of diagnostic and prognostic techniques that utilitiescan adopted in lieu of labor-intense periodic preventive main-tenance routines. Furthermore, prognostic models have beenincorporated using the latest version of the Institute of Elec-trical and Electronics Engineers (IEEE) standard (IEEE StdC57.104TM-2019) for dissolved gas analysis (DGA), thusexpanding it to include estimation of the time to maintenance.Overall, four different methodologies are explained, each ofwhich aid in determining a transformer’s state of health. Thesemethodologies include the Chendong model, the IEEE C57.91-2011 thermal life consumption model, a diagnostic model forDGA, and a prognostic model for DGA that uses an autore-gressive integrated moving average (ARIMA) model. An ad-ditional improvement for estimating missing system parame-ters from monitoring data (i.e., a tool for parameter estimationutilizing Powell’s method) is presented, enabling the IEEEthermal life consumption model to benefit not only the col-laborating power plant, but also the power industry at large.
{"title":"Transformer Health Monitoring Using Dissolved Gas Analysis","authors":"C. Walker, Ahmad Y. Al Rashdan, V. Agarwal","doi":"10.36001/ijphm.2022.v13i2.3141","DOIUrl":"https://doi.org/10.36001/ijphm.2022.v13i2.3141","url":null,"abstract":"As integral components of any power plant, transformers sup-ply the generated electricity to the grid. However, the trans-former’s cellulose-based paper insulation and the mineral oilin which it is immersed break down over time under stan-dard operating conditions—or more rapidly due to potentialfaults within the system. This technical brief exhibits a col-lection of diagnostic and prognostic techniques that utilitiescan adopted in lieu of labor-intense periodic preventive main-tenance routines. Furthermore, prognostic models have beenincorporated using the latest version of the Institute of Elec-trical and Electronics Engineers (IEEE) standard (IEEE StdC57.104TM-2019) for dissolved gas analysis (DGA), thusexpanding it to include estimation of the time to maintenance.Overall, four different methodologies are explained, each ofwhich aid in determining a transformer’s state of health. Thesemethodologies include the Chendong model, the IEEE C57.91-2011 thermal life consumption model, a diagnostic model forDGA, and a prognostic model for DGA that uses an autore-gressive integrated moving average (ARIMA) model. An ad-ditional improvement for estimating missing system parame-ters from monitoring data (i.e., a tool for parameter estimationutilizing Powell’s method) is presented, enabling the IEEEthermal life consumption model to benefit not only the col-laborating power plant, but also the power industry at large.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2022-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46855339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-07DOI: 10.36001/ijphm.2022.v13i2.3132
Haihua Ou, D. Gates, S. Johnson, D. Djurdjanović
This study proposes a novel method for monitoring muscle fatigue using muscle-specific dynamic models which relate joint time-frequency signatures extracted from the relevant electromyogram (EMG) signals with the corresponding estimated muscle forces. Muscle forces were estimated using physics-driven musculoskeletal models which incorporate muscle lengths and contraction velocities estimated from the available kinematic and kinetic measurements. For any specific individual, such a muscle-specific dynamic model is trained using EMG and movement data collected in the early stages of an exercise, i.e., during the least-fatigued behavior. As the exercise or physical activity of that individual progresses and fatigue develops, residuals yielded by that model when approximating the newly arrived data shift and change because of the fatigue-induced changes in the underlying dynamics. In this paper, we propose quantitative evaluation of those changes via the concept of a muscle-specific Freshness Index (FI) which at any given time expresses overlaps between the distribution of that muscle’s model residuals observed on the most recently collected data and the distribution of modeling residuals observed during non-fatigued behavior. The newly proposed method was evaluated using data collected during a repetitive sawing motion experiment with 12 healthy participants. The performance of the FI as a fatigue metric was compared with the performance of the instantaneous frequency of the relevant EMG signals, which is a more traditional and widely used metric of muscle fatigue. It was found that the FI reflected the progression of muscle fatigue with desirable properties of stronger monotonic trends and smaller noise levels compared to the traditional, instantaneous frequency-based metrics.
{"title":"Model-based Fusion of Surface Electromyography with Kinematic and Kinetic Measurements for Monitoring of Muscle Fatigue","authors":"Haihua Ou, D. Gates, S. Johnson, D. Djurdjanović","doi":"10.36001/ijphm.2022.v13i2.3132","DOIUrl":"https://doi.org/10.36001/ijphm.2022.v13i2.3132","url":null,"abstract":"This study proposes a novel method for monitoring muscle fatigue using muscle-specific dynamic models which relate joint time-frequency signatures extracted from the relevant electromyogram (EMG) signals with the corresponding estimated muscle forces. Muscle forces were estimated using physics-driven musculoskeletal models which incorporate muscle lengths and contraction velocities estimated from the available kinematic and kinetic measurements. For any specific individual, such a muscle-specific dynamic model is trained using EMG and movement data collected in the early stages of an exercise, i.e., during the least-fatigued behavior. As the exercise or physical activity of that individual progresses and fatigue develops, residuals yielded by that model when approximating the newly arrived data shift and change because of the fatigue-induced changes in the underlying dynamics. In this paper, we propose quantitative evaluation of those changes via the concept of a muscle-specific Freshness Index (FI) which at any given time expresses overlaps between the distribution of that muscle’s model residuals observed on the most recently collected data and the distribution of modeling residuals observed during non-fatigued behavior. The newly proposed method was evaluated using data collected during a repetitive sawing motion experiment with 12 healthy participants. The performance of the FI as a fatigue metric was compared with the performance of the instantaneous frequency of the relevant EMG signals, which is a more traditional and widely used metric of muscle fatigue. It was found that the FI reflected the progression of muscle fatigue with desirable properties of stronger monotonic trends and smaller noise levels compared to the traditional, instantaneous frequency-based metrics.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2022-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45541305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-10DOI: 10.36001/ijphm.2022.v13i1.3134
Tedja Verhulst, D. Judt, C. Lawson, Yongmann M. Chung, Osama Al-Tayawe, Geoff Ward
Aircraft maintenance is an essential cost borne by the airline. Improving maintenance practices for day-to-day operations can lead to significant financial savings. The benefits of effective maintenance are derived from the avoided costs caused by unexpected breakdowns and from maximising aircraft flight time transporting passengers. The fuel system is a crucial part of the entire aircraft as it ensures delivery of the fuel to the engine and a key component within this system are the fuel pumps. These airborne fuel pumps are classified between the pumps installed in the airframe fuel system and in the engine fuel system. Past works have investigated the performance characteristics of these pumps during flight, however there are no reviews related to the present Health Monitoring (HM) capabilities under flight conditions. HM refers to the field of diagnosing faults or predicting the remaining useful life (RUL) of the pump and the focus of this review is to highlight the HM technologies suitable for aircraft fuel pumps. This is done by first reviewing the technologies and concepts related to HM of fuel pumps. Second a literature review is carried out on pump and motor faults is carried out, drawing on examples from aerospace and other relevant industries. Section 6: Conclusion, discusses the HM technologies have been applied to aerospace fuel pumps and highlights the gaps in capabilities, based on the findings of the literature review carried out in Section 4: Common Faults and Section 5: HM Sensing Methods to suggest future developments in this field. It was found that there is a large scope for development for the HM airframe fuel pumps, based on reviewing the present state of the art. Furthermore, there are no clear strategies formulated by airframe manufacturers and equipment suppliers to test and implement existing HM solutions to operate under flight conditions. This highlights the need to develop HM in this field and a requirement for further research to allow this technology to be a part of routine aircraft
{"title":"Review for State-of-the-Art Health Monitoring Technologies on Airframe Fuel Pumps","authors":"Tedja Verhulst, D. Judt, C. Lawson, Yongmann M. Chung, Osama Al-Tayawe, Geoff Ward","doi":"10.36001/ijphm.2022.v13i1.3134","DOIUrl":"https://doi.org/10.36001/ijphm.2022.v13i1.3134","url":null,"abstract":"Aircraft maintenance is an essential cost borne by the airline. Improving maintenance practices for day-to-day operations can lead to significant financial savings. The benefits of effective maintenance are derived from the avoided costs caused by unexpected breakdowns and from maximising aircraft flight time transporting passengers. The fuel system is a crucial part of the entire aircraft as it ensures delivery of the fuel to the engine and a key component within this system are the fuel pumps. These airborne fuel pumps are classified between the pumps installed in the airframe fuel system and in the engine fuel system. Past works have investigated the performance characteristics of these pumps during flight, however there are no reviews related to the present Health Monitoring (HM) capabilities under flight conditions. HM refers to the field of diagnosing faults or predicting the remaining useful life (RUL) of the pump and the focus of this review is to highlight the HM technologies suitable for aircraft fuel pumps. This is done by first reviewing the technologies and concepts related to HM of fuel pumps. Second a literature review is carried out on pump and motor faults is carried out, drawing on examples from aerospace and other relevant industries. Section 6: Conclusion, discusses the HM technologies have been applied to aerospace fuel pumps and highlights the gaps in capabilities, based on the findings of the literature review carried out in Section 4: Common Faults and Section 5: HM Sensing Methods to suggest future developments in this field. It was found that there is a large scope for development for the HM airframe fuel pumps, based on reviewing the present state of the art. Furthermore, there are no clear strategies formulated by airframe manufacturers and equipment suppliers to test and implement existing HM solutions to operate under flight conditions. This highlights the need to develop HM in this field and a requirement for further research to allow this technology to be a part of routine aircraft","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47043810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-08DOI: 10.36001/ijphm.2022.v13i1.3120
C. Walker, P. Ramuhalli, Vivek Agarwal, N. Lybeck, Mike Taylor
Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.
{"title":"Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection","authors":"C. Walker, P. Ramuhalli, Vivek Agarwal, N. Lybeck, Mike Taylor","doi":"10.36001/ijphm.2022.v13i1.3120","DOIUrl":"https://doi.org/10.36001/ijphm.2022.v13i1.3120","url":null,"abstract":"Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. \u0000This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2022-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41766966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-31DOI: 10.36001/ijphm.2022.v13i1.3064
Rushikesh Pawar, R. Patil, Dhananjay Y. Patil, Aditi Rahegaonkar, S. Pardeshi, A. Patange
Road traffic injuries and deaths are a growing public health concern worldwide, majorly in developing countries. Brake failure constitutes to be one of the primary reasons for accidents. The majority of brake failures are caused due to overheating of the brakes, while wear of lining is another big share-holder. Early detection of such causes can prevent these accidents. This study puts forth a model that can be used for onboard monitoring of drum/disc temperature & lining/pad thickness by taking velocity & road inclination in real-time as inputs. Many quantities are interdependent and vary with respect to time/temperature. Therefore, an incremental approach is used. The model is implemented in the Simulink software. Many standard profiles are also fed to compare results for different terrains and driving conditions. The drivers can also be classified based on their driving behavior. The thermal model can give us an early warning about the brake overheating. This model can be used to study the energy distribution while braking. Researchers and designers can also use this model to study & optimize the brake system.
{"title":"Development of a Model for Predicting Brake Friction Lining Thickness and Brake Temperature","authors":"Rushikesh Pawar, R. Patil, Dhananjay Y. Patil, Aditi Rahegaonkar, S. Pardeshi, A. Patange","doi":"10.36001/ijphm.2022.v13i1.3064","DOIUrl":"https://doi.org/10.36001/ijphm.2022.v13i1.3064","url":null,"abstract":"Road traffic injuries and deaths are a growing public health concern worldwide, majorly in developing countries. Brake failure constitutes to be one of the primary reasons for accidents. The majority of brake failures are caused due to overheating of the brakes, while wear of lining is another big share-holder. Early detection of such causes can prevent these accidents. This study puts forth a model that can be used for onboard monitoring of drum/disc temperature & lining/pad thickness by taking velocity & road inclination in real-time as inputs. Many quantities are interdependent and vary with respect to time/temperature. Therefore, an incremental approach is used. The model is implemented in the Simulink software. Many standard profiles are also fed to compare results for different terrains and driving conditions. The drivers can also be classified based on their driving behavior. The thermal model can give us an early warning about the brake overheating. This model can be used to study the energy distribution while braking. Researchers and designers can also use this model to study & optimize the brake system.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2022-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46626298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-30DOI: 10.36001/ijphm.2022.v13i1.3115
Miguel Simão, Rune Prytz, Sławomir Nowaczyk
In this paper, we present and evaluate a novel methodology to estimate the usable capacity and state-of-health (SOH) of lithium-ion batteries in battery-electric buses (BEV). This methodology is designed to be applicable to any BEV in normal operation, independently of battery chemistry, and without requiring complex electrochemical models or large data sets. We have tested the proposed methodology on two vehicle fleets with a total of 105 vehicles, for which we have been acquiring data for up to three years. Additionally, we have analysed the operation of the fleets in terms of daily distance driven and the charging strategies chosen by the operators.The monitored vehicles are part of fleets currently in normal operation in Europe. The data collection is done with a third-party data logger that is connected to the vehicles’ Communication Area Network (CAN) buses, and no additional changes were made to the vehicle’s hardware or software. The results show that the proposed methodology shows significantly lower variance in SOH estimation than the alternative methodologies. It also shows similar accuracy in the long-term and smaller short-term deviations from the typical capacity fade model.
{"title":"Long-term Evaluation of the State-of-Health of Traction Lithium-ion Batteries in Operational Buses","authors":"Miguel Simão, Rune Prytz, Sławomir Nowaczyk","doi":"10.36001/ijphm.2022.v13i1.3115","DOIUrl":"https://doi.org/10.36001/ijphm.2022.v13i1.3115","url":null,"abstract":"In this paper, we present and evaluate a novel methodology to estimate the usable capacity and state-of-health (SOH) of lithium-ion batteries in battery-electric buses (BEV). This methodology is designed to be applicable to any BEV in normal operation, independently of battery chemistry, and without requiring complex electrochemical models or large data sets. We have tested the proposed methodology on two vehicle fleets with a total of 105 vehicles, for which we have been acquiring data for up to three years. Additionally, we have analysed the operation of the fleets in terms of daily distance driven and the charging strategies chosen by the operators.The monitored vehicles are part of fleets currently in normal operation in Europe. The data collection is done with a third-party data logger that is connected to the vehicles’ Communication Area Network (CAN) buses, and no additional changes were made to the vehicle’s hardware or software. The results show that the proposed methodology shows significantly lower variance in SOH estimation than the alternative methodologies. It also shows similar accuracy in the long-term and smaller short-term deviations from the typical capacity fade model.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2022-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42636744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-23DOI: 10.36001/ijphm.2022.v13i1.3107
A. Sattarifar, T. Nestorović
Identification of damage in its early stage can have a great contribution in decreasing the maintenance costs and prolonging the life of valuable structures. Although conventional damage detection techniques have a mature background, their widespread application in industrial practice is still missing. In recent years the application of Machine Learning (ML) algorithms have been more and more exploited in structural health monitoring systems (SHM). Because of the superior capabilities of ML approaches in recognizing and classifying available patterns in a dataset, they have demonstrated a significant improvement in traditional damage identification algorithms. This review study focuses on the use of machine learning (ML) approaches in Ultrasonic Guided Wave (UGW)-based SHM, in which a structure is continually monitored using permanent sensors. Accordingly, multiple steps required for performing damage detection through UGWs are stated. Moreover, it is outlined that the employment of ML techniques for UGW-based damage detection can be subtended into two main phases: (1) extracting features from the data set, and reducing the dimension of the data space, (2) processing the patterns for revealing patterns, and classification of instances. With this regard, the most frequent techniques for the realization of those two phases are elaborated. This study shows the great potential of ML algorithms to assist and enhance UGW-based damage detection algorithms.
{"title":"Emergence of Machine Learning Techniques in Ultrasonic Guided Wave-based Structural Health Monitoring","authors":"A. Sattarifar, T. Nestorović","doi":"10.36001/ijphm.2022.v13i1.3107","DOIUrl":"https://doi.org/10.36001/ijphm.2022.v13i1.3107","url":null,"abstract":"Identification of damage in its early stage can have a great contribution in decreasing the maintenance costs and prolonging the life of valuable structures. Although conventional damage detection techniques have a mature background, their widespread application in industrial practice is still missing. In recent years the application of Machine Learning (ML) algorithms have been more and more exploited in structural health monitoring systems (SHM). Because of the superior capabilities of ML approaches in recognizing and classifying available patterns in a dataset, they have demonstrated a significant improvement in traditional damage identification algorithms. This review study focuses on the use of machine learning (ML) approaches in Ultrasonic Guided Wave (UGW)-based SHM, in which a structure is continually monitored using permanent sensors. Accordingly, multiple steps required for performing damage detection through UGWs are stated. Moreover, it is outlined that the employment of ML techniques for UGW-based damage detection can be subtended into two main phases: (1) extracting features from the data set, and reducing the dimension of the data space, (2) processing the patterns for revealing patterns, and classification of instances. With this regard, the most frequent techniques for the realization of those two phases are elaborated. This study shows the great potential of ML algorithms to assist and enhance UGW-based damage detection algorithms.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42052885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-13DOI: 10.36001/ijphm.2022.v13i1.3106
Roohollah Heidarydashtarjandi, Jubilee Prasad-Rao, K. Groth
This paper presents a novel approach to determine optimal maintenance policies for degraded oil and gas pipelines due to internal pitting corrosion. This approach builds a bridge between Markov process-based corrosion rate models and Markov decision processes (MDP). This bridging allows for the consideration of both short-term and long-term costs for optimal pipeline maintenance operations. To implement MDP, probability transition matrices are estimated to move from one degradation state to the next in the pipeline degradation Markov processes. A case study is also implemented with four pipeline failure modes (i.e., safe, small leak, large leak, and rupture). And four maintenance actions (i.e. do nothing, adding corrosion inhibitors, pigging, and replacement) are considered by assuming perfect pipeline inspections. Monte Carlo simulation is performed on 10,000 initial pits using the selected corrosion models and assumed maintenance and failure costs to determine an optimal maintenance policy.
{"title":"Optimal Maintenance Policy for Corroded Oil and Gas Pipelines using Markov Decision Processes","authors":"Roohollah Heidarydashtarjandi, Jubilee Prasad-Rao, K. Groth","doi":"10.36001/ijphm.2022.v13i1.3106","DOIUrl":"https://doi.org/10.36001/ijphm.2022.v13i1.3106","url":null,"abstract":"This paper presents a novel approach to determine optimal maintenance policies for degraded oil and gas pipelines due to internal pitting corrosion. This approach builds a bridge between Markov process-based corrosion rate models and Markov decision processes (MDP). This bridging allows for the consideration of both short-term and long-term costs for optimal pipeline maintenance operations. To implement MDP, probability transition matrices are estimated to move from one degradation state to the next in the pipeline degradation Markov processes. A case study is also implemented with four pipeline failure modes (i.e., safe, small leak, large leak, and rupture). And four maintenance actions (i.e. do nothing, adding corrosion inhibitors, pigging, and replacement) are considered by assuming perfect pipeline inspections. Monte Carlo simulation is performed on 10,000 initial pits using the selected corrosion models and assumed maintenance and failure costs to determine an optimal maintenance policy.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2022-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47695339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-20DOI: 10.36001/ijphm.2019.v10i3.2705
Kai-Wen Yang, L. Nicolini, Irene Kuang, N. Lu, D. Djurdjanović
This paper introduces stretchable, long-term wearable, tattoo-like dry surface electrodes for highly repeatable electromyography (EMG). The tattoo-like sensors are hair thin, skin compliant and can be laminated on human skin just like a temporary transfer tattoo, which enables multi-day noninvasive but intimate contact with the skin even under severe skin deformation. The new electrodes were used to facilitate a system-based approach to tracking of long-term fatiguing and recovery processes in a human neuromusculoskeletal (NMS) system, which was based on establishing an autoregressive moving average model with exogenous inputs (ARMAX model) relating signatures extracted from the surface electromyogram (sEMG) signals collected using the tattoo-like sensors, and the corresponding hand grip force (HGF) serving as the model output. Performance degradation of the relevant NMS system was evaluated by tracking the evolution of the errors of the ARMAX model established using the data corresponding to the rested (fresh) state of any given subject. Results from several exercise sessions clearly showed repeated patterns of fatiguing and resting, with a notable point that these patterns could now be quantified via dynamic models relating the relevant muscle signatures and NMS outputs.
{"title":"Long-Term Modeling and Monitoring of Neuromusculoskeletal System Performance Using Tattoo-Like EMG Sensors","authors":"Kai-Wen Yang, L. Nicolini, Irene Kuang, N. Lu, D. Djurdjanović","doi":"10.36001/ijphm.2019.v10i3.2705","DOIUrl":"https://doi.org/10.36001/ijphm.2019.v10i3.2705","url":null,"abstract":"This paper introduces stretchable, long-term wearable, tattoo-like dry surface electrodes for highly repeatable electromyography (EMG). The tattoo-like sensors are hair thin, skin compliant and can be laminated on human skin just like a temporary transfer tattoo, which enables multi-day noninvasive but intimate contact with the skin even under severe skin deformation. The new electrodes were used to facilitate a system-based approach to tracking of long-term fatiguing and recovery processes in a human neuromusculoskeletal (NMS) system, which was based on establishing an autoregressive moving average model with exogenous inputs (ARMAX model) relating signatures extracted from the surface electromyogram (sEMG) signals collected using the tattoo-like sensors, and the corresponding hand grip force (HGF) serving as the model output. Performance degradation of the relevant NMS system was evaluated by tracking the evolution of the errors of the ARMAX model established using the data corresponding to the rested (fresh) state of any given subject. Results from several exercise sessions clearly showed repeated patterns of fatiguing and resting, with a notable point that these patterns could now be quantified via dynamic models relating the relevant muscle signatures and NMS outputs.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2022-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42964989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-25DOI: 10.36001/ijphm.2022.v13i1.3072
T. Loutas, Athanasios Oikonomou, N. Eleftheroglou, F. Freeman, D. Zarouchas
We investigate the performance of three different data-driven prognostic methodologies towards the Remaining Useful Life estimation of commercial aircraft brakes being continuously monitored for wear. The first approach utilizes a probabilistic multi-state deterioration mathematical model i.e. a Hidden Semi Markov model whilst the second utilizes a nonlinear regression approach through classical Artificial Neural Networks in a Bootstrap fashion in order to obtain prediction intervals to accompany the mean remaining life estimates. The third approach attempts to leverage the highly linear degradation data over time and uses a simple linear regression in a Bayesian framework. All methodologies, when properly trained with historical degradation data, achieve excellent performance in terms of early and accurate prediction of the remaining useful flights that the monitored set of brakes can safely serve. The paper presents a real-world application where it is demonstrated that even in non-complex linear degradation data the inherent data stochasticity prohibits the use of a simple mathematical approaches and asks for methodologies with uncertainty quantification.
{"title":"Remaining Useful Life Prognosis of Aircraft Brakes","authors":"T. Loutas, Athanasios Oikonomou, N. Eleftheroglou, F. Freeman, D. Zarouchas","doi":"10.36001/ijphm.2022.v13i1.3072","DOIUrl":"https://doi.org/10.36001/ijphm.2022.v13i1.3072","url":null,"abstract":"We investigate the performance of three different data-driven prognostic methodologies towards the Remaining Useful Life estimation of commercial aircraft brakes being continuously monitored for wear. The first approach utilizes a probabilistic multi-state deterioration mathematical model i.e. a Hidden Semi Markov model whilst the second utilizes a nonlinear regression approach through classical Artificial Neural Networks in a Bootstrap fashion in order to obtain prediction intervals to accompany the mean remaining life estimates. The third approach attempts to leverage the highly linear degradation data over time and uses a simple linear regression in a Bayesian framework. All methodologies, when properly trained with historical degradation data, achieve excellent performance in terms of early and accurate prediction of the remaining useful flights that the monitored set of brakes can safely serve. The paper presents a real-world application where it is demonstrated that even in non-complex linear degradation data the inherent data stochasticity prohibits the use of a simple mathematical approaches and asks for methodologies with uncertainty quantification.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2022-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47646191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：