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
We have carried out at laboratory test to study the feasibility of using thermal radiation detectors for online thermal monitoring of electrical systems in wind turbines. A 25 kW frequency converter is instrumented wi...We have carried out at laboratory test to study the feasibility of using thermal radiation detectors for online thermal monitoring of electrical systems in wind turbines. A 25 kW frequency converter is instrumented with a thermal camera, operating in the 8-14 μm wave- length range, and a single-pixel thermopile sensor, operating in the 4-8 μm wavelength range, to monitor the temperature development of the power electronics under various load sequences. Both systems performed satisfactorily with insignificant temperature deviations when compared to data from calibrated point contact sensor. With spatial averaging over a 7 mm × 7 mm for the camera and temporal averaging over 60 s for the thermo- pile sensor, we reduce the root mean square noise to 45 mK and 68 mK respectively. The low cost and simple operation of the thermopile sensor make it very attractive for condition monitoring applications, whereas the attractive feature of the camera is the possibility of multi-point or distributed temperature measurements.展开更多
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.
文摘We have carried out at laboratory test to study the feasibility of using thermal radiation detectors for online thermal monitoring of electrical systems in wind turbines. A 25 kW frequency converter is instrumented with a thermal camera, operating in the 8-14 μm wave- length range, and a single-pixel thermopile sensor, operating in the 4-8 μm wavelength range, to monitor the temperature development of the power electronics under various load sequences. Both systems performed satisfactorily with insignificant temperature deviations when compared to data from calibrated point contact sensor. With spatial averaging over a 7 mm × 7 mm for the camera and temporal averaging over 60 s for the thermo- pile sensor, we reduce the root mean square noise to 45 mK and 68 mK respectively. The low cost and simple operation of the thermopile sensor make it very attractive for condition monitoring applications, whereas the attractive feature of the camera is the possibility of multi-point or distributed temperature measurements.
