Adaptive Calibration of Soft Sensors Using Optimal Transportation Transfer Learning for Mass Production and Long‐Term Usage

Abstract

Soft sensors suffer from high manufacturing tolerances and signal drift from long‐term usage, which degrades their practicality. Although deep learning has recently been proposed to address these issues, it is expensive in terms of data collection and processing. Therefore, an adaptive calibration method is proposed for soft sensors, suitable for mass production and long‐term usage. In addition to maintaining the original benefits of deep learning characterization, this method enables fast and accurate calibration by capturing the change in the characteristics of the sensor through domain adaptation, using optimal transportation. An offline calibration method is first described, which is for alleviating the difficulty in calibrating every single unit from mass produced soft sensors. The main advantage is that identically manufactured soft sensors in a large volume with variations can be calibrated with reduced time and effort for collecting and processing data. Online calibration is then discussed, which compensates for the parameter changes when a soft sensor is continuously used for an extended period of time. For a single sensor, even though the sensor shows signal drift from the long‐term usage, the calibrated network weights can be quickly adjusted online. Finally, the proposed adaptive calibration is experimentally evaluated using actual soft sensors.

Heterogeneous sensing in a multifunctional soft sensor for human-robot interfaces

“…An automated manufacturing process, such as direct patterning of liquid conductors (12,68,86) or embedded 3D printing (18,87,88), will be highly useful to increase the uniformity of the product in this case. Furthermore, a transfer learning technique (89) can be used for calibrating multiple sensors with variations more efficiently, which will save a considerable amount of time and resources when compared with traditional calibration methods.…”

Review of machine learning methods in soft robotics

“…This learning method was able to reduce training time and efficiently process large dataset, while maintaining superior sensing performance. Kim et al also used an optimal transportation transfer learning to learn the model of soft sensors with large volume [ 54 ].…”

Electronic skins and machine learning for intelligent soft robots

“…At the level of abstraction of the entire robotic system, Van Meerbeek et al tested various learning algorithms to estimate the twist and bend angles in sensorized foam, finding that k nearest neighbors (kNN) outperformed other common algorithms including support vector machines (SVM) and multilayer perceptrons (MLP) (55). In addition, Kim et al, Soter et al, Thuruthel et al, and Kim et al, focused on recurrent neural networks, which have been shown to be advantageous for learning patterns in time series data (9,12,64,65).…”