Dynamic Placement of Rapidly Deployable Mobile Sensor Robots Using Machine Learning and Expected Value of Information

11/15/2021
by   Alice Agogino, et al.
0

Although the Industrial Internet of Things has increased the number of sensors permanently installed in industrial plants, there will be gaps in coverage due to broken sensors or sparse density in very large plants, such as in the petrochemical industry. Modern emergency response operations are beginning to use Small Unmanned Aerial Systems (sUAS) that have the ability to drop sensor robots to precise locations. sUAS can provide longer-term persistent monitoring that aerial drones are unable to provide. Despite the relatively low cost of these assets, the choice of which robotic sensing systems to deploy to which part of an industrial process in a complex plant environment during emergency response remains challenging. This paper describes a framework for optimizing the deployment of emergency sensors as a preliminary step towards realizing the responsiveness of robots in disaster circumstances. AI techniques (Long short-term memory, 1-dimensional convolutional neural network, logistic regression, and random forest) identify regions where sensors would be most valued without requiring humans to enter the potentially dangerous area. In the case study described, the cost function for optimization considers costs of false-positive and false-negative errors. Decisions on mitigation include implementing repairs or shutting down the plant. The Expected Value of Information (EVI) is used to identify the most valuable type and location of physical sensors to be deployed to increase the decision-analytic value of a sensor network. This method is applied to a case study using the Tennessee Eastman process data set of a chemical plant, and we discuss implications of our findings for operation, distribution, and decision-making of sensors in plant emergency and resilience scenarios.

READ FULL TEXT

page 4

page 13

research
03/18/2016

A Probabilistic Machine Learning Approach to Detect Industrial Plant Faults

Fault detection in industrial plants is a hot research area as more and ...
research
08/05/2020

A Novel Method For Designing Transferable Soft Sensors And Its Application

In this paper, a new approach is proposed for designing transferable sof...
research
04/28/2021

EmergencyNet: Efficient Aerial Image Classification for Drone-Based Emergency Monitoring Using Atrous Convolutional Feature Fusion

Deep learning-based algorithms can provide state-of-the-art accuracy for...
research
06/20/2019

Deep-Learning-Based Aerial Image Classification for Emergency Response Applications Using Unmanned Aerial Vehicles

Unmanned Aerial Vehicles (UAVs), equipped with camera sensors can facili...
research
08/05/2022

The Value and Use of Data in Chemical Engineering Practice

The ability to generate, organize, analyze, understand and leverage data...
research
08/01/2022

Networked Drones for Industrial Emergency Events

Uncontrolled emissions of gases from industrial accidents and disasters ...
research
11/08/2019

Hierarchical network design for nitrogen dioxide measurement in urban environments, part 2: network-based sensor calibration

We present a management and data correction framework for low-cost elect...

Please sign up or login with your details

Forgot password? Click here to reset