In the era of Industry 4.0,conditionmonitoring has emerged as an effective solution for process industries to optimize their operational efficiency.Condition monitoring helps minimize unplanned downtime,extending equi...In the era of Industry 4.0,conditionmonitoring has emerged as an effective solution for process industries to optimize their operational efficiency.Condition monitoring helps minimize unplanned downtime,extending equipment lifespan,reducing maintenance costs,and improving production quality and safety.This research focuses on utilizing Bayesian search-based machine learning and deep learning approaches for the condition monitoring of industrial equipment.The study aims to enhance predictive maintenance for industrial equipment by forecasting vibration values based on domain-specific feature engineering.Early prediction of vibration enables proactive interventions to minimize downtime and extend the lifespan of critical assets.A data set of load information and vibration values from a heavy-duty industrial slip ring induction motor(4600 kW)and gearbox equipped with vibration sensors is used as a case study.The study implements and compares six machine learning models with the proposed Bayesian-optimized stacked Long Short-Term Memory(LSTM)model.The hyperparameters used in the implementation of models are selected based on the Bayesian optimization technique.Comparative analysis reveals that the proposed Bayesian optimized stacked LSTM outperforms other models,showcasing its capability to learn temporal features as well as long-term dependencies in time series information.The implemented machine learning models:Linear Regression(LR),RandomForest(RF),Gradient Boosting Regressor(GBR),ExtremeGradient Boosting(XGBoost),Light Gradient Boosting Machine(LightGBM),and Support Vector Regressor(SVR)displayed a mean squared error of 0.9515,0.4654,0.1849,0.0295,0.2127 and 0.0273,respectively.The proposed model predicts the future vibration characteristics with a mean squared error of 0.0019 on the dataset containing motor load information and vibration characteristics.The results demonstrate that the proposed model outperforms other models in terms of other evaluation metrics with a mean absolute error of 0.0263 and 0.882 as a coefficient of determination.Current research not only contributes to the comparative performance of machine learning models in condition monitoring but also showcases the practical implications of employing these techniques.By transitioning fromreactive to proactive maintenance strategies,industries canminimize downtime,reduce costs,and prolong the lifespan of crucial assets.This study demonstrates the practical advantages of transitioning from reactive to proactive maintenance strategies using ML-based condition monitoring.展开更多
The volume of rail traffic was increased by 5 % from 2006 to 2010, in Sweden, due to increased goods and passenger traffic. This increased traffic, in turn, has led to a more rapid degradation of the railway track, wh...The volume of rail traffic was increased by 5 % from 2006 to 2010, in Sweden, due to increased goods and passenger traffic. This increased traffic, in turn, has led to a more rapid degradation of the railway track, which has resulted in higher maintenance costs. In general, degradation affects comfort, safety, and track quality, as well as, reliability, availability, speed, and overall railway performance. This case study investigated the needs of railway stakeholders responsible for analysing the track state and what information is necessary to make good maintenance decisions. The goal is to improve the railway track per- formance by ensuring increased availability, reliability, and safety, along with a decreased maintenance cost. Inter- views of eight experts were undertaken to learn of general areas in need of improvement, and a quantitative analysis of condition monitoring data was conducted to find more specific information. The results show that by implement- ing a long-term maintenance strategy and by conducting preventive maintenance actions maintenance costs would be reduced. In addition to that, problems with measured data, missing data, and incorrect location data resulted in increased and unnecessary maintenance tasks. The conclusions show that proactive solutions are needed to reach the desired goals of improved safety, improved availability, and improved reliability. This also includes thedevelopment of a visualisation tool and a life cycle cost model for maintenance strategies.展开更多
Most of the machineries in small or large-scale industry have rotating elementsupported by bearings for rigid support and accurate movement. For proper functioning ofmachinery, condition monitoring of the bearing is v...Most of the machineries in small or large-scale industry have rotating elementsupported by bearings for rigid support and accurate movement. For proper functioning ofmachinery, condition monitoring of the bearing is very important. In present study soundsignal is used to continuously monitor bearing health as sound signals of rotatingmachineries carry dynamic information of components. There are numerous studies inliterature that are reporting superiority of vibration signal of bearing fault diagnosis.However, there are very few studies done using sound signal. The cost associated withcondition monitoring using sound signal (Microphone) is less than the cost of transducerused to acquire vibration signal (Accelerometer). This paper employs sound signal forcondition monitoring of roller bearing by K-star classifier and k-nearest neighborhoodclassifier. The statistical feature extraction is performed from acquired sound signals. Thentwo-layer feature selection is done using J48 decision tree algorithm and random treealgorithm. These selected features were classified using K-star classifier and k-nearestneighborhood classifier and parametric optimization is performed to achieve the maximumclassification accuracy. The classification results for both K-star classifier and k-nearestneighborhood classifier for condition monitoring of roller bearing using sound signals werecompared.展开更多
文摘In the era of Industry 4.0,conditionmonitoring has emerged as an effective solution for process industries to optimize their operational efficiency.Condition monitoring helps minimize unplanned downtime,extending equipment lifespan,reducing maintenance costs,and improving production quality and safety.This research focuses on utilizing Bayesian search-based machine learning and deep learning approaches for the condition monitoring of industrial equipment.The study aims to enhance predictive maintenance for industrial equipment by forecasting vibration values based on domain-specific feature engineering.Early prediction of vibration enables proactive interventions to minimize downtime and extend the lifespan of critical assets.A data set of load information and vibration values from a heavy-duty industrial slip ring induction motor(4600 kW)and gearbox equipped with vibration sensors is used as a case study.The study implements and compares six machine learning models with the proposed Bayesian-optimized stacked Long Short-Term Memory(LSTM)model.The hyperparameters used in the implementation of models are selected based on the Bayesian optimization technique.Comparative analysis reveals that the proposed Bayesian optimized stacked LSTM outperforms other models,showcasing its capability to learn temporal features as well as long-term dependencies in time series information.The implemented machine learning models:Linear Regression(LR),RandomForest(RF),Gradient Boosting Regressor(GBR),ExtremeGradient Boosting(XGBoost),Light Gradient Boosting Machine(LightGBM),and Support Vector Regressor(SVR)displayed a mean squared error of 0.9515,0.4654,0.1849,0.0295,0.2127 and 0.0273,respectively.The proposed model predicts the future vibration characteristics with a mean squared error of 0.0019 on the dataset containing motor load information and vibration characteristics.The results demonstrate that the proposed model outperforms other models in terms of other evaluation metrics with a mean absolute error of 0.0263 and 0.882 as a coefficient of determination.Current research not only contributes to the comparative performance of machine learning models in condition monitoring but also showcases the practical implications of employing these techniques.By transitioning fromreactive to proactive maintenance strategies,industries canminimize downtime,reduce costs,and prolong the lifespan of crucial assets.This study demonstrates the practical advantages of transitioning from reactive to proactive maintenance strategies using ML-based condition monitoring.
文摘The volume of rail traffic was increased by 5 % from 2006 to 2010, in Sweden, due to increased goods and passenger traffic. This increased traffic, in turn, has led to a more rapid degradation of the railway track, which has resulted in higher maintenance costs. In general, degradation affects comfort, safety, and track quality, as well as, reliability, availability, speed, and overall railway performance. This case study investigated the needs of railway stakeholders responsible for analysing the track state and what information is necessary to make good maintenance decisions. The goal is to improve the railway track per- formance by ensuring increased availability, reliability, and safety, along with a decreased maintenance cost. Inter- views of eight experts were undertaken to learn of general areas in need of improvement, and a quantitative analysis of condition monitoring data was conducted to find more specific information. The results show that by implement- ing a long-term maintenance strategy and by conducting preventive maintenance actions maintenance costs would be reduced. In addition to that, problems with measured data, missing data, and incorrect location data resulted in increased and unnecessary maintenance tasks. The conclusions show that proactive solutions are needed to reach the desired goals of improved safety, improved availability, and improved reliability. This also includes thedevelopment of a visualisation tool and a life cycle cost model for maintenance strategies.
文摘Most of the machineries in small or large-scale industry have rotating elementsupported by bearings for rigid support and accurate movement. For proper functioning ofmachinery, condition monitoring of the bearing is very important. In present study soundsignal is used to continuously monitor bearing health as sound signals of rotatingmachineries carry dynamic information of components. There are numerous studies inliterature that are reporting superiority of vibration signal of bearing fault diagnosis.However, there are very few studies done using sound signal. The cost associated withcondition monitoring using sound signal (Microphone) is less than the cost of transducerused to acquire vibration signal (Accelerometer). This paper employs sound signal forcondition monitoring of roller bearing by K-star classifier and k-nearest neighborhoodclassifier. The statistical feature extraction is performed from acquired sound signals. Thentwo-layer feature selection is done using J48 decision tree algorithm and random treealgorithm. These selected features were classified using K-star classifier and k-nearestneighborhood classifier and parametric optimization is performed to achieve the maximumclassification accuracy. The classification results for both K-star classifier and k-nearestneighborhood classifier for condition monitoring of roller bearing using sound signals werecompared.
