Pub Date : 2022-06-29DOI: 10.36001/phme.2022.v7i1.3331
Lukas Lodes, Alexander Schiendorfer
Machine Learning (ML), in particular classification with deep neural nets, can be applied to a variety of industrial tasks. It can augment established methods for controlling manufacturing processes such as statistical process control (SPC) to detect non-obvious patterns in high-dimensional input data. However, due to the widespread issue of model miscalibration in neural networks, there is a need for estimating the predictive uncertainty of these models. Many established approaches for uncertainty estimation output scores that are difficult to put into actionable insight. We therefore introduce the concept of certainty groups which distinguish the predictions of a neural network into the normal group and the certainty group. The certainty group contains only predictions with a very high accuracy that can be set up to 100%. We present an approach to compute these certainty groups and demonstrate our approach on two datasets from a PHM setting.
{"title":"Certainty Groups: A Practical Approach to Distinguish Confidence Levels in Neural Networks","authors":"Lukas Lodes, Alexander Schiendorfer","doi":"10.36001/phme.2022.v7i1.3331","DOIUrl":"https://doi.org/10.36001/phme.2022.v7i1.3331","url":null,"abstract":"Machine Learning (ML), in particular classification with deep neural nets, can be applied to a variety of industrial tasks. It can augment established methods for controlling manufacturing processes such as statistical process control (SPC) to detect non-obvious patterns in high-dimensional input data. However, due to the widespread issue of model miscalibration in neural networks, there is a need for estimating the predictive uncertainty of these models. Many established approaches for uncertainty estimation output scores that are difficult to put into actionable insight. We therefore introduce the concept of certainty groups which distinguish the predictions of a neural network into the normal group and the certainty group. The certainty group contains only predictions with a very high accuracy that can be set up to 100%. We present an approach to compute these certainty groups and demonstrate our approach on two datasets from a PHM setting.","PeriodicalId":422825,"journal":{"name":"PHM Society European Conference","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115971545","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 : 2022-06-29DOI: 10.36001/phme.2022.v7i1.3367
M. Asres, G. Cummings, A. Khukhunaishvili, P. Parygin, S. Cooper, D. Yu, J. Dittmann, C. Omlin
Predictive maintenance is essential for complex industrial systems to foresee anomalies before major system faults or ultimate breakdown. However, the existing efforts on Industry 4.0 predictive monitoring are directed at semi-supervised anomaly detection with limited robustness for large systems, which are often accompanied by uncleaned and unlabeled data. We address the challenge of predicting anomalies through data-driven end-to-end deep learning models using early warning symptoms on multivariate time series sensor data. We introduce AnoP, a long multi-timestep anomaly prediction system based on unsupervised attention-based causal residual networks, to raise alerts for anomaly prevention. The experimental evaluation on large data sets from detector health monitoring of the Hadron Calorimeter of the CMS Experiment at LHC CERN demonstrates the promising efficacy of the proposed approach. AnoP predicted around 60% of the anomalies up to seven days ahead, and the majority of the missed anomalies are abnormalities with unpredictable noisy-like behavior. Moreover, it has discovered previously unknown anomalies in the calorimeter’s sensors.
{"title":"Long Horizon Anomaly Prediction in Multivariate Time Series with Causal Autoencoders","authors":"M. Asres, G. Cummings, A. Khukhunaishvili, P. Parygin, S. Cooper, D. Yu, J. Dittmann, C. Omlin","doi":"10.36001/phme.2022.v7i1.3367","DOIUrl":"https://doi.org/10.36001/phme.2022.v7i1.3367","url":null,"abstract":"Predictive maintenance is essential for complex industrial systems to foresee anomalies before major system faults or ultimate breakdown. However, the existing efforts on Industry 4.0 predictive monitoring are directed at semi-supervised anomaly detection with limited robustness for large systems, which are often accompanied by uncleaned and unlabeled data. We address the challenge of predicting anomalies through data-driven end-to-end deep learning models using early warning symptoms on multivariate time series sensor data. We introduce AnoP, a long multi-timestep anomaly prediction system based on unsupervised attention-based causal residual networks, to raise alerts for anomaly prevention. The experimental evaluation on large data sets from detector health monitoring of the Hadron Calorimeter of the CMS Experiment at LHC CERN demonstrates the promising efficacy of the proposed approach. AnoP predicted around 60% of the anomalies up to seven days ahead, and the majority of the missed anomalies are abnormalities with unpredictable noisy-like behavior. Moreover, it has discovered previously unknown anomalies in the calorimeter’s sensors.","PeriodicalId":422825,"journal":{"name":"PHM Society European Conference","volume":"212 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116428031","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 : 2022-06-29DOI: 10.36001/phme.2022.v7i1.3323
M. Camargos, P. Angelov
Lithium-ion batteries are key energy storage elements in the context of environmental-aware energy systems representing a crucial technology to achieve the goal of zero carbon emission. Therefore, its conditions must be monitored to guarantee the safe and reliable operation of the systems that use these components. Furthermore, lithium-ion batteries’ prognostics and health management policies must cope with the nonlinear and time-varying nature of the complex electrochemical dynamics of battery degradation. This paper proposes an incremental-learning-based algorithm to estimate the State of Health (SoH) and the Remaining Useful Life (RUL) of lithium-ion batteries based on measurement data streams. For this purpose, a two-layer framework is proposed based on incremental modeling of the SoH. In the first layer, a set of representative features are extracted from voltage and current data of partial charging and discharging cycles; these features are then used to train the proposed model in a recursive procedure to estimate the battery’s SoH. The second layer uses the capacity data for incremental learning of an Autoregressive (AR) model for the SoH, which will be used to propagate the battery’s degradation through time to make the RUL prediction. The proposed method was applied to two datasets for experimental evaluation, one from CALCE and another from NASA. The proposed framework was able to estimate the SoH of 8 different lithium-ion cells with an average percentage error below 1.5% for all scenarios, while the lifetime model predicted the cell’s RUL with a maximum average error of 25%.
{"title":"State of Health and Lifetime Prediction of Lithium-ion Batteries Using Self-learning Incremental Models","authors":"M. Camargos, P. Angelov","doi":"10.36001/phme.2022.v7i1.3323","DOIUrl":"https://doi.org/10.36001/phme.2022.v7i1.3323","url":null,"abstract":"Lithium-ion batteries are key energy storage elements in the context of environmental-aware energy systems representing a crucial technology to achieve the goal of zero carbon emission. Therefore, its conditions must be monitored to guarantee the safe and reliable operation of the systems that use these components. Furthermore, lithium-ion batteries’ prognostics and health management policies must cope with the nonlinear and time-varying nature of the complex electrochemical dynamics of battery degradation. This paper proposes an incremental-learning-based algorithm to estimate the State of Health (SoH) and the Remaining Useful Life (RUL) of lithium-ion batteries based on measurement data streams. For this purpose, a two-layer framework is proposed based on incremental modeling of the SoH. In the first layer, a set of representative features are extracted from voltage and current data of partial charging and discharging cycles; these features are then used to train the proposed model in a recursive procedure to estimate the battery’s SoH. The second layer uses the capacity data for incremental learning of an Autoregressive (AR) model for the SoH, which will be used to propagate the battery’s degradation through time to make the RUL prediction. The proposed method was applied to two datasets for experimental evaluation, one from CALCE and another from NASA. The proposed framework was able to estimate the SoH of 8 different lithium-ion cells with an average percentage error below 1.5% for all scenarios, while the lifetime model predicted the cell’s RUL with a maximum average error of 25%.","PeriodicalId":422825,"journal":{"name":"PHM Society European Conference","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123558415","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 : 2022-06-29DOI: 10.36001/phme.2022.v7i1.3332
Zahra Taghiyarrenani, A. Berenji
Selecting the physical property capable of representing the health state of a machine is an important step in designing fault detection systems. In addition, variation of the loading condition is a challenge in deploying an industrial predictive maintenance solution. The robustness of the physical properties to variations in loading conditions is, therefore, an important consideration. In this paper, we focus specifically on squirrel cage induction motors and analyze the capabilities of three-phase current and five vibration signals acquired from different locations of the motor for the detection of Broken Rotor Bar generated in different loads. In particular, we examine the mentioned signals in relation to the performance of classifiers trained with them. Regarding the classifiers, we employ deep conventional classifiers and also propose a hybrid classifier that utilizes contrastive loss in order to mitigate the effect of different variations. The analysis shows that vibration signals are more robust under varying load conditions. Furthermore, the proposed hybrid classifier outperforms conventional classifiers and is able to achieve an accuracy of 90.96% when using current signals and 97.69% when using vibration signals.
{"title":"Analysis of Vibrations and Currents for Broken Rotor Bar Detection in Three-phase Induction Motors","authors":"Zahra Taghiyarrenani, A. Berenji","doi":"10.36001/phme.2022.v7i1.3332","DOIUrl":"https://doi.org/10.36001/phme.2022.v7i1.3332","url":null,"abstract":"Selecting the physical property capable of representing the health state of a machine is an important step in designing fault detection systems. In addition, variation of the loading condition is a challenge in deploying an industrial predictive maintenance solution. The robustness of the physical properties to variations in loading conditions is, therefore, an important consideration. In this paper, we focus specifically on squirrel cage induction motors and analyze the capabilities of three-phase current and five vibration signals acquired from different locations of the motor for the detection of Broken Rotor Bar generated in different loads. In particular, we examine the mentioned signals in relation to the performance of classifiers trained with them. Regarding the classifiers, we employ deep conventional classifiers and also propose a hybrid classifier that utilizes contrastive loss in order to mitigate the effect of different variations. The analysis shows that vibration signals are more robust under varying load conditions. Furthermore, the proposed hybrid classifier outperforms conventional classifiers and is able to achieve an accuracy of 90.96% when using current signals and 97.69% when using vibration signals.","PeriodicalId":422825,"journal":{"name":"PHM Society European Conference","volume":"711 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123840545","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 : 2022-06-29DOI: 10.36001/phme.2022.v7i1.3347
L. Baldo, P. Berri, M. D. Dalla Vedova, P. Maggiore
The growing adoption of electrical energy as a secondary form of onboard power leads to an increase of electromechanical actuators (EMAs) use in aerospace applications. Therefore, innovative prognostic and diagnostic methodologies are becoming a fundamental tool to early identify faults propagation, prevent performance degradation, and ensure an acceptable level of safety and reliability of the system. Furthermore, prognostics entails further advantages, including a better ability to plan the maintenance of the various equipment, manage the warehouse and maintenance personnel, and a reduction in system management costs. Frequently, such approaches require the development of typologies of numerical models capable of simulating the performance of the EMA with different levels of fidelity: monitoring models, suitably simplified to combine speed and accuracy with reduced computational costs, and high fidelity models (and high computational intensity), to generate databases, develop predictive algorithms and train machine learning surrogates. Because of this, the authors developed a high-fidelity multi-domain numerical model (HF) capable of accounting for a variety of physical phenomena and gradual failures in the EMA, as well as a low-fidelity counterpart (LF). This simplified model is derived by the HF and intended for monitoring applications. While maintaining a low computing cost, LF is fault sensitive and can simulate the system position, speed, and equivalent phase currents. These models have been validated using a dedicated EMA test bench, designed and implemented by authors. The HF model can simulate the operation of the actuator in nominal conditions as well as in the presence of incipient mechanical faults, such as a variation in friction and an increase of backlash in the reduction gearbox. Comparing the preliminary results highlights satisfactory consistency between the experimental test bench and the two numerical models proposed by the authors.
{"title":"Experimental Validation of Multi-fidelity Models for Prognostics of Electromechanical Actuators","authors":"L. Baldo, P. Berri, M. D. Dalla Vedova, P. Maggiore","doi":"10.36001/phme.2022.v7i1.3347","DOIUrl":"https://doi.org/10.36001/phme.2022.v7i1.3347","url":null,"abstract":"The growing adoption of electrical energy as a secondary form of onboard power leads to an increase of electromechanical actuators (EMAs) use in aerospace applications. Therefore, innovative prognostic and diagnostic methodologies are becoming a fundamental tool to early identify faults propagation, prevent performance degradation, and ensure an acceptable level of safety and reliability of the system. Furthermore, prognostics entails further advantages, including a better ability to plan the maintenance of the various equipment, manage the warehouse and maintenance personnel, and a reduction in system management costs.\u0000Frequently, such approaches require the development of typologies of numerical models capable of simulating the performance of the EMA with different levels of fidelity: monitoring models, suitably simplified to combine speed and accuracy with reduced computational costs, and high fidelity models (and high computational intensity), to generate databases, develop predictive algorithms and train machine learning surrogates. Because of this, the authors developed a high-fidelity multi-domain numerical model (HF) capable of accounting for a variety of physical phenomena and gradual failures in the EMA, as well as a low-fidelity counterpart (LF). This simplified model is derived by the HF and intended for monitoring applications. While maintaining a low computing cost, LF is fault sensitive and can simulate the system position, speed, and equivalent phase currents.\u0000These models have been validated using a dedicated EMA test bench, designed and implemented by authors. The HF model can simulate the operation of the actuator in nominal conditions as well as in the presence of incipient mechanical faults, such as a variation in friction and an increase of backlash in the reduction gearbox.\u0000Comparing the preliminary results highlights satisfactory consistency between the experimental test bench and the two numerical models proposed by the authors.","PeriodicalId":422825,"journal":{"name":"PHM Society European Conference","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121425942","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 : 2022-06-29DOI: 10.36001/phme.2022.v7i1.3328
Manuel S. Mathew, S. Kandukuri, C. Omlin
In this paper, we estimate the age-related performance degradation of a wind turbine working under Norwegian environment, based on a deep neural network model. Ten years of high-resolution operational data from a 2 MW wind turbine were used for the analysis. Operational data of the turbine, between cut-in and rated wind velocities, were considered, which were pre-processed to eliminate outliers and noises. Based on the SHapley Additive exPlanations of a preliminary performance model, a benchmark performance model for the turbine was developed with deep neural networks. An efficiency index is proposed to gauge the agerelated performance degradation of the turbine, which compares measured performances of the turbine over the years with corresponding bench marked performance. On an average, the efficiency index of the turbine is found to decline by 0.64 percent annually, which is comparable with the degradation patterns reported under similar studies from the UK and the US.
{"title":"Estimation of Wind Turbine Performance Degradation with Deep Neural Networks","authors":"Manuel S. Mathew, S. Kandukuri, C. Omlin","doi":"10.36001/phme.2022.v7i1.3328","DOIUrl":"https://doi.org/10.36001/phme.2022.v7i1.3328","url":null,"abstract":"In this paper, we estimate the age-related performance degradation of a wind turbine working under Norwegian environment, based on a deep neural network model. Ten years of high-resolution operational data from a 2 MW wind turbine were used for the analysis. Operational data of the turbine, between cut-in and rated wind velocities, were considered, which were pre-processed to eliminate outliers and noises. Based on the SHapley Additive exPlanations of a preliminary performance model, a benchmark performance model for the turbine was developed with deep neural networks. An efficiency index is proposed to gauge the agerelated performance degradation of the turbine, which compares measured performances of the turbine over the years with corresponding bench marked performance. On an average, the efficiency index of the turbine is found to decline by 0.64 percent annually, which is comparable with the degradation patterns reported under similar studies from the UK and the US.","PeriodicalId":422825,"journal":{"name":"PHM Society European Conference","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122521993","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 : 2022-06-29DOI: 10.36001/phme.2022.v7i1.3372
Immo Schmidt, Lorenz Dingeldein, D. Hünemohr, Henrik Simon, Max Weigert
For the data challenge of the 2022 European PHM conference, data from a production line of electric circuit boards is provided to assess the quality of the produced components. The solution presented in this paper was elaborated to fulfill the data challenge objectives of predicting defects found in an automatic inspection at the end of the production line, predicting the result of a following human inspection and predicting the result of the repair of the defect components. Machine learning methods are used to accomplish the different prediction tasks. In order to build a reliable machine learning model, the steps of data preparation, feature engineering and model selection are performed. Finally, different models are chosen and implemented for the different sub-tasks. The prediction of defects in the automatic inspection is modeled with a multi-layer perceptron neural network, the prediction of human inspection is modeled using a random forest algorithm. For the prediction of human repair, a decision tree is implemented.
{"title":"Application of Machine Learning Methods to Predict the Quality of Electric Circuit Boards of a Production Line","authors":"Immo Schmidt, Lorenz Dingeldein, D. Hünemohr, Henrik Simon, Max Weigert","doi":"10.36001/phme.2022.v7i1.3372","DOIUrl":"https://doi.org/10.36001/phme.2022.v7i1.3372","url":null,"abstract":"For the data challenge of the 2022 European PHM conference, data from a production line of electric circuit boards is provided to assess the quality of the produced components. The solution presented in this paper was elaborated to fulfill the data challenge objectives of predicting defects found in an automatic inspection at the end of the production line, predicting the result of a following human inspection and predicting the result of the repair of the defect components. Machine learning methods are used to accomplish the different prediction tasks. In order to build a reliable machine learning model, the steps of data preparation, feature engineering and model selection are performed. Finally, different models are chosen and implemented for the different sub-tasks. The prediction of defects in the automatic inspection is modeled with a multi-layer perceptron neural network, the prediction of human inspection is modeled using a random forest algorithm. For the prediction of human repair, a decision tree is implemented.","PeriodicalId":422825,"journal":{"name":"PHM Society European Conference","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126496587","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 : 2022-06-29DOI: 10.36001/phme.2022.v7i1.3344
R. Kulkarni, R. Giossi, Prapanpong Damsongsaeng, A. Qazizadeh, M. Berg
Intelligent fault identification of rail vehicles from onboard measurements is of utmost importance to reduce the operating and maintenance cost of high-speed vehicles. Early identification of vehicle faults responsible for an unsafe situation, such as the instable running of highspeed vehicles, is very important to ensure the safety of operating rail vehicles. However, this task is challenging because of the nonlinear dynamics associated with multiple subsystems of the rail vehicle. The task becomes more challenging with only accelerations recorded in the carbody where, nevertheless, sensor maintenance is significantly lower compared to axlebox accelerometers. This paper proposes a Temporal Convolution Network (TCN)-based intelligent fault detection algorithm to detect rail vehicle faults. In this investigation, the classifiers are trained and tested with the results of numerical simulations of a high-speed vehicle (200 km/h). The TCN based fault classification algorithm identifies the rail vehicle faults with 98.7% accuracy. The proposed method contributes towards digitalization of rail vehicle maintenance through condition-based and predictive maintenance.
{"title":"iVRIDA: intelligent Vehicle Running Instability Detection Algorithm for High-speed Rail Vehicles using Temporal Convolution Network – A Pilot Study","authors":"R. Kulkarni, R. Giossi, Prapanpong Damsongsaeng, A. Qazizadeh, M. Berg","doi":"10.36001/phme.2022.v7i1.3344","DOIUrl":"https://doi.org/10.36001/phme.2022.v7i1.3344","url":null,"abstract":"Intelligent fault identification of rail vehicles from onboard measurements is of utmost importance to reduce the operating and maintenance cost of high-speed vehicles. Early identification of vehicle faults responsible for an unsafe situation, such as the instable running of highspeed vehicles, is very important to ensure the safety of operating rail vehicles. However, this task is challenging because of the nonlinear dynamics associated with multiple subsystems of the rail vehicle. The task becomes more challenging with only accelerations recorded in the carbody where, nevertheless, sensor maintenance is significantly lower compared to axlebox accelerometers. This paper proposes a Temporal Convolution Network (TCN)-based intelligent fault detection algorithm to detect rail vehicle faults. In this investigation, the classifiers are trained and tested with the results of numerical simulations of a high-speed vehicle (200 km/h). The TCN based fault classification algorithm identifies the rail vehicle faults with 98.7% accuracy. The proposed method contributes towards digitalization of rail vehicle maintenance through condition-based and predictive maintenance.","PeriodicalId":422825,"journal":{"name":"PHM Society European Conference","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124584765","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 : 2022-06-29DOI: 10.36001/phme.2022.v7i1.3368
C. Ruiz-Carcel, A. Starr, A. Francese
Modern rotorcrafts rely on Health and Usage Monitoring Systems (HUMS) to enhance their availability, reliability, and safety. In those systems, data related to the health of key mechanical components is acquired, in addition to typical flight condition history data such as speed and torque. Commercial HUM systems usually rely on vibration measurements to assess the condition of shafts, gears, and bearings; using techniques such as spectral analysis, harmonic analysis, vibration trend and others. Recent research has shown that acoustic emissions (AE) can be advantageous in the detection of mechanical faults, in particular detecting very early small defects on bearings and gears, providing extra time for maintenance planning. However, the addition of extra sensors adds complexity and weight to the HUMS system, which is undesirable. This research is an experimental study to assess the monitoring capabilities of a broadband sensor, able to cover both low frequency vibration components as well as ultrasonic events, hence combining the benefits of both in a single compact sensing unit. The experimental results obtained from an instrumented rig using healthy components as well as seeded faults show the ability of the sensor to detect high frequency events, and compares the performance of the sensor in the low frequency range with a commercial accelerometer.
{"title":"Experimental Assessment of a Broadband Vibration and Acoustic Emission Sensor for Rotorcraft Transmission Monitoring","authors":"C. Ruiz-Carcel, A. Starr, A. Francese","doi":"10.36001/phme.2022.v7i1.3368","DOIUrl":"https://doi.org/10.36001/phme.2022.v7i1.3368","url":null,"abstract":"Modern rotorcrafts rely on Health and Usage Monitoring Systems (HUMS) to enhance their availability, reliability, and safety. In those systems, data related to the health of key mechanical components is acquired, in addition to typical flight condition history data such as speed and torque. Commercial HUM systems usually rely on vibration measurements to assess the condition of shafts, gears, and bearings; using techniques such as spectral analysis, harmonic analysis, vibration trend and others. Recent research has shown that acoustic emissions (AE) can be advantageous in the detection of mechanical faults, in particular detecting very early small defects on bearings and gears, providing extra time for maintenance planning. However, the addition of extra sensors adds complexity and weight to the HUMS system, which is undesirable. This research is an experimental study to assess the monitoring capabilities of a broadband sensor, able to cover both low frequency vibration components as well as ultrasonic events, hence combining the benefits of both in a single compact sensing unit. The experimental results obtained from an instrumented rig using healthy components as well as seeded faults show the ability of the sensor to detect high frequency events, and compares the performance of the sensor in the low frequency range with a commercial accelerometer.","PeriodicalId":422825,"journal":{"name":"PHM Society European Conference","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117349624","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 : 2022-06-29DOI: 10.36001/phme.2022.v7i1.3327
N. Noori, V. Shanbhag, S. Kandukuri, R. Schlanbusch
The work presented in this paper is built on a series of experiments aiming to develop a data-driven and automated method for seal diagnostics using Acoustic Emission (AE) features. Seals in machineries operate in harsh conditions, and seal wear in hydraulic cylinders results in fluid leakage, and instability of the piston rod movement. Therefore, regular inspection of seals is required using automated approaches to improve productivity and to reduce unscheduled maintenance. In this study, we implemented a data-driven diagnostics approach which utilizes AE measurements along with light weight Artificial Neural Networks (ANN) as a classifier to investigate the performance and resources (hardware & software) required for implementing a real-time soft sensor unit for monitoring seal wear condition. We used a feedforward multilayer perceptron ANN (Scaled Conjugate Gradient- SCG algorithm) that is trained with the back propagation algorithm, which is a popular network architecture for a multitude of applications (automotive, oil and gas, electronics). We benchmark the developed method against previous work conducted based on Support Vector Machine (SVM), and we compare ANN performance in classifying the running condition of seals in hydraulic cylinders by applying it to both raw (full frequency spectrum) and down sampled frequency measurements. The experiments were performed at varying pressure conditions on a hydraulic test rig that can simulate fluid leakage conditions like that of hydraulic cylinders. The test cases were generated with seals of three different conditions (unworn, semi-worn, worn). From the AE spectrum, the frequency bands were identified with peak power and by heterodyning the signal. This technique results in 10X down sampling without losing the information of interest. Further, the signal was divided into smaller “snapshots” to facilitate rapid diagnosis. In these tests, the diagnosis was made on short-time windows, as low as 0.3 seconds in length. A general set of 16 time and frequency domain features were designed. Then a training set was developed using relevant set of features (4, 5, and 16 features). The data was used to train the ANN (70% training – 30% test & validation) and SVM (60 % training - 40% test and validation). Classification of down sampled measurements, both ANN and SVM were able to accurately classify the status irrespective of the pressure conditions, with an accuracy of ~99% with execution time less than seconds. Therefore, the proposed approach can be applied as part of an automated seal wear classification technique based on AE and ANN/SVM and can be used for real-time monitoring of seal wear in hydraulic cylinders.
{"title":"Data Driven Seal Wear Classifications using Acoustic Emissions and Artificial Neural Networks","authors":"N. Noori, V. Shanbhag, S. Kandukuri, R. Schlanbusch","doi":"10.36001/phme.2022.v7i1.3327","DOIUrl":"https://doi.org/10.36001/phme.2022.v7i1.3327","url":null,"abstract":"The work presented in this paper is built on a series of experiments aiming to develop a data-driven and automated method for seal diagnostics using Acoustic Emission (AE) features. Seals in machineries operate in harsh conditions, and seal wear in hydraulic cylinders results in fluid leakage, and instability of the piston rod movement. Therefore, regular inspection of seals is required using automated approaches to improve productivity and to reduce unscheduled maintenance. In this study, we implemented a data-driven diagnostics approach which utilizes AE measurements along with light weight Artificial Neural Networks (ANN) as a classifier to investigate the performance and resources (hardware & software) required for implementing a real-time soft sensor unit for monitoring seal wear condition. We used a feedforward multilayer perceptron ANN (Scaled Conjugate Gradient- SCG algorithm) that is trained with the back propagation algorithm, which is a popular network architecture for a multitude of applications (automotive, oil and gas, electronics). We benchmark the developed method against previous work conducted based on Support Vector Machine (SVM), and we compare ANN performance in classifying the running condition of seals in hydraulic cylinders by applying it to both raw (full frequency spectrum) and down sampled frequency measurements. The experiments were performed at varying pressure conditions on a hydraulic test rig that can simulate fluid leakage conditions like that of hydraulic cylinders. The test cases were generated with seals of three different conditions (unworn, semi-worn, worn). From the AE spectrum, the frequency bands were identified with peak power and by heterodyning the signal. This technique results in 10X down sampling without losing the information of interest. Further, the signal was divided into smaller “snapshots” to facilitate rapid diagnosis. In these tests, the diagnosis was made on short-time windows, as low as 0.3 seconds in length. A general set of 16 time and frequency domain features were designed. Then a training set was developed using relevant set of features (4, 5, and 16 features). The data was used to train the ANN (70% training – 30% test & validation) and SVM (60 % training - 40% test and validation). Classification of down sampled measurements, both ANN and SVM were able to accurately classify the status irrespective of the pressure conditions, with an accuracy of ~99% with execution time less than seconds. Therefore, the proposed approach can be applied as part of an automated seal wear classification technique based on AE and ANN/SVM and can be used for real-time monitoring of seal wear in hydraulic cylinders.","PeriodicalId":422825,"journal":{"name":"PHM Society European Conference","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133237961","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：