Dynamic Field Monitoring Based on Multitask Learning in Sensor Networks

Abstract

Field monitoring serves as an important supervision tool in a variety of engineering domains. An efficient monitoring would trigger an alarm timely once it detects an out-of-control event by learning the state change from the collected sensor data. However, in practice, multiple sensor data may not be gathered appropriately into a database for some unexpected reasons, such as sensor aging, wireless communication failures, and data reading errors, which leads to a large number of missing data as well as inaccurate or delayed detection, and poses a great challenge for field monitoring in sensor networks. This fact motivates us to develop a multitask-learning based field monitoring method in order to achieve an efficient detection when considerable missing data exist during data acquisition. Specifically, we adopt a log likelihood ratio (LR)-based multivariate cumulative sum (MCUSUM) control chart given spatial correlation among neighboring regions within the monitored field. To deal with the missing data problem, we integrate a multitask learning model into the LR-based MCUSUM control chart in the sensor network. Both simulation and real case studies are conducted to validate our proposed approach and the results show that our approach can achieve an accurate and timely detection for an out-of-control state when a large number of missing data exist in the sensor database. Our model provides an effective field monitoring strategy for engineering applications to accurately and timely detect the products with abnormal quality during production and reduce product losses.

Automatic Anomaly Detection on In-Production Manufacturing Machines Using Statistical Learning Methods

“…One of the most common approaches for statistical anomaly detection is based on the control chart [3], with applications ranging from industrial machines [5,8] to identifying contaminants [6] to farming [4] and multiple others. Contrary to most popular control chart approaches [8], in our case, we did not deal with multivariate data.…”

“…Automatic systems for anomaly detection can give relevant advantages to manufacturing companies by reducing their down-time due to machine breakdowns and by detecting a failure before this results in a catastrophic event, and this is enabled without the need for resorting to the work of expensive human experts in the field [1,2]. Popular methods for anomaly detection include both traditional control statistics, like the control chart [3][4][5][6][7][8], and machine learning (and most recently deep learning) methods [2,[9][10][11][12], like for instance autoencoders [13], support vector machines [14], and convolutional and recurrent neural networks [15,16].…”