The performance of data-driven fault detection and diagnostics(FDD)is heavily dependent on sensors.However,sensor inaccuracy and sensor faults are pervasive in building operation:inaccurate and missing sensor readings...The performance of data-driven fault detection and diagnostics(FDD)is heavily dependent on sensors.However,sensor inaccuracy and sensor faults are pervasive in building operation:inaccurate and missing sensor readings deteriorate FDD performance;sensor inaccuracy will also affect the selection of sensor for data-driven FDD in the model training process,which is another key factor of data-driven FDD performance.Sensor accuracy and sensor selection individually are well-studied research topics in this field,but the impact of sensor accuracy on sensor selection and its further impact on FDD performance has not been evaluated and quantified.In this paper,we developed a novel analysis methodology that comprehensively evaluates sensor fault on sensor selection and FDD accuracy.Monte Carlo simulation is applied to deal with multiple stochastic sensor inaccuracy and provide probabilistic analysis results of the impact of sensor inaccuracy on sensor selection and FDD accuracy.This methodology focuses on the net impact of fault states across a full sensor set.The developed methodology can be used for the early-stage sensor design and operation-stage sensor maintenance.A case study is conducted to demonstrate the analysis methodology using a commercial building model crated to Flexible Research Platform located at Oak Ridge National Laboratory,USA.展开更多
Accurate position measurements are extremely valuable in the shipping industry for various reasons such as safety(collision avoidance),security(situational awareness),fuel-saving(weather identification),punctuality(ro...Accurate position measurements are extremely valuable in the shipping industry for various reasons such as safety(collision avoidance),security(situational awareness),fuel-saving(weather identification),punctuality(route prediction),etc.Although GNSS(Global Navigation Satellite System)receivers installed on-board the ships are proven to be highly accurate,the data logging process may occasionally be problematic,mainly due to the complexity of the measurements and the decimal precision that is required.Data were collected from 3 years of operations of 228 Maersk Line container vessels and an analysis reveals that there is a substantial amount (≈20%) of historical position measurements sent to shore that does not reflect reality.In the study,the sources of the faulty logged position measurements are categorized and an interpolation methodology is proposed to validate and correct them by using AIS(Automatic Identification System)data.展开更多
文摘The performance of data-driven fault detection and diagnostics(FDD)is heavily dependent on sensors.However,sensor inaccuracy and sensor faults are pervasive in building operation:inaccurate and missing sensor readings deteriorate FDD performance;sensor inaccuracy will also affect the selection of sensor for data-driven FDD in the model training process,which is another key factor of data-driven FDD performance.Sensor accuracy and sensor selection individually are well-studied research topics in this field,but the impact of sensor accuracy on sensor selection and its further impact on FDD performance has not been evaluated and quantified.In this paper,we developed a novel analysis methodology that comprehensively evaluates sensor fault on sensor selection and FDD accuracy.Monte Carlo simulation is applied to deal with multiple stochastic sensor inaccuracy and provide probabilistic analysis results of the impact of sensor inaccuracy on sensor selection and FDD accuracy.This methodology focuses on the net impact of fault states across a full sensor set.The developed methodology can be used for the early-stage sensor design and operation-stage sensor maintenance.A case study is conducted to demonstrate the analysis methodology using a commercial building model crated to Flexible Research Platform located at Oak Ridge National Laboratory,USA.
基金supported by“InnovationsFonden Danmark”with case number 8053-00231B and“Den Danske Maritime Fond”with case number 2018-060.
文摘Accurate position measurements are extremely valuable in the shipping industry for various reasons such as safety(collision avoidance),security(situational awareness),fuel-saving(weather identification),punctuality(route prediction),etc.Although GNSS(Global Navigation Satellite System)receivers installed on-board the ships are proven to be highly accurate,the data logging process may occasionally be problematic,mainly due to the complexity of the measurements and the decimal precision that is required.Data were collected from 3 years of operations of 228 Maersk Line container vessels and an analysis reveals that there is a substantial amount (≈20%) of historical position measurements sent to shore that does not reflect reality.In the study,the sources of the faulty logged position measurements are categorized and an interpolation methodology is proposed to validate and correct them by using AIS(Automatic Identification System)data.
