Automatic False-Alarm Labeling for Sensor Data
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
A false alarm, which is an incorrect report of an emergency, could trigger an unnecessary action. The predictive maintenance framework developed in our previous work has a feature whereby a machine alarm is triggered based on sensor data evaluation. The sensor data evaluator performs three essential evaluation steps. First, it evaluates each sensor data value based on its threshold (lower and upper bound) and labels the data value as “alarm” when the threshold is exceeded. Second, it calculates the duration of the occurrence of the alarm. Finally, in the third step, a domain expert is required to assess the results from the previous two steps and to determine, thereby, whether the alarm is true or false. There are drawbacks of the current evaluation method. It suffers from a high false-alarm ratio, and moreover, given the vast amount of sensor data to be assessed by the domain expert, the process of evaluation is prolonged and inefficient. In this paper, we propose a method for automatic false-alarm labeling that mimics how the domain expert determines false alarms. The domain expert determines false alarms by evaluating two critical factors, specifically the duration of alarm occurrence and identification of anomalies before or while the alarm occurs. In our proposed method, Hierarchical Temporal Memory (HTM) is utilized to detect anomalies. It is an unsupervised approach that is suitable to our main data characteristic, which is the lack of an example of the normal form of sensor data. The result shows that the technique is effective for automatic labeling of false alarms in sensor data.
Abstract
A false alarm, which is an incorrect report of an emergency, could trigger an unnecessary action. The predictive maintenance framework developed in our previous work has a feature whereby a machine alarm is triggered based on sensor data evaluation. The sensor data evaluator performs three essential evaluation steps. First, it evaluates each sensor data value based on its threshold (lower and upper bound) and labels the data value as “alarm” when the threshold is exceeded. Second, it calculates the duration of the occurrence of the alarm. Finally, in the third step, a domain expert is required to assess the results from the previous two steps and to determine, thereby, whether the alarm is true or false. There are drawbacks of the current evaluation method. It suffers from a high false-alarm ratio, and moreover, given the vast amount of sensor data to be assessed by the domain expert, the process of evaluation is prolonged and inefficient. In this paper, we propose a method for automatic false-alarm labeling that mimics how the domain expert determines false alarms. The domain expert determines false alarms by evaluating two critical factors, specifically the duration of alarm occurrence and identification of anomalies before or while the alarm occurs. In our proposed method, Hierarchical Temporal Memory (HTM) is utilized to detect anomalies. It is an unsupervised approach that is suitable to our main data characteristic, which is the lack of an example of the normal form of sensor data. The result shows that the technique is effective for automatic labeling of false alarms in sensor data.
참고문헌 (28)
- ISA, "ANSI", ISA-18.2: Management of Alarm Systems for the Process Industries, 2009
- Nochur, A., "Alarm performance metrics", Honeywell Singapore, ~ (2001)
- Jain, P., "Did we learn about risk control since Seveso? Yes, we surely did, but is it enough? An historical brief and problem analysis", Journal of Loss Prevention in the Process Industries (2016)
- Stauffer, T., "Get a Life (cycle)!Connecting Alarm Management and Safety Instrumented Systems", Paper presented at the ISA Safety & Security Symposium (2010)
- Srinivasan, R., "Intelligent alarm management in a petroleum refinery", Hydrocarbon Processing, 83(11), pp.47~54 (2004)
- EEMUA, "191-Alarm Systems: A Guide to Design, Management and Procurement Edition 3", ~ (2013)
- Pariyani, A., "Incidents Investigation and Dynamic Analysis of Large Alarm Databases in Chemical Plants: A Fluidized-Catalytic-Cracking Unit Case Study", Industrial & Engineering Chemistry Research, 49(17), pp.8062~8079 (2010)
- S. Haque, "False Alarm Detection in Cyber-physical Systems for Healthcare Applications", AASRI Procedia, 5, pp.54~61 (2013)
- S. Festag, "False alarm ratio of fire detection and fire alarm systems in Germany – A meta analysis", Fire Safety Journal, 79, pp.119~126 (2016)
- R. Pokrywka, "Reducing False Alarm Rate in Anomaly Detection with Layered Filtering", Computational Science – ICCS 2008, pp.396~404 (2008)
- A. Patcha, "An overview of anomaly detection techniques: Existing solutions and latest technological trends", Comput. Netw, 51(12), pp.3448~3470 (2007)
- J. Lin, "Approximations to magic: finding unusual medical time series", 18th IEEE Symposium on Computer-Based Medical Systems (CBMS’05) (2005), IEEE
- J. Wu, "Hierarchical Temporal Memory method for time-series-based anomaly detection", ~ (2018)
- S. Ahmad, "Unsupervised real-time anomaly detection for streaming data", Neurocomputing, 262, pp.134~147 (2017)
- D. Rothenberg, "Alarm Management for Process Control" (2011), Momentum Press
- Jiandong Wang, "An Overview of Industrial Alarm Systems: Main Causes for Alarm Overloading, Research Status, and Open Problems", IEEE Transactions on Automation Science and Engineering, 13(2), pp.1045~1061 (2016), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- T. Adi, "Cloud-Based Predictive Maintenance Framework for Sensor Data Analytics", ICIC Express Letters, Part B: Applications, 9(11), pp.1161~ (2018)
- V. Chandola, "Anomaly detection:a survey", ACM Comput.Surv. (CSUR), 41(3), pp.15~ (2009)
- V. Hodge, "A survey of outlier detection methodologies", Artif. Intell. Rev, 22(2), pp.85~126 (2004)
- J. Hawkins, "Why neurons have thousands of synapses, a theory of sequence memory in neocortex", Front. Neural Circ, 10 (2016)
- J. Hawkins, "Hierarchical Temporal Memory White Paper" (2011), Numenta
- Jenkins, S., "Guidelines for Engineering Design for Process Safety", Chemical Engineering, 119(9), pp.9~10 (2012)
- Stauffer, T., "Using alarms as a layer of protection", Process Safety Progress (2015)
- Nochur, A., "Alarm performance metrics" (2001), Honeywell Singapore
- P. Goel, "Industrial alarm systems : Challenges and opportunities", Journal of Loss Prevention in the Process Industries, 50, pp.23~36 (2017)
- S. Ahmad, "Real-Time Anomaly Detection for Streaming Analytics", arXiv:1607.02480, ~ (2016)
- "2015", ~
- "Numenta GitHub repository"[URL]