Development of Self-Calibrating Smart Sensors for Industrial Automation using Kalman Filtering and Sensor Fusion
Yui Kimura, Michael Schmidt · Computer Science Bulletin · 2026
Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.
Computer Science Bulletin · OpenAlex · article · 2026
Abstract
The rapid advancement of Industry 4.0 has necessitated the deployment of highly accurate and reliable sensor networks to monitor complex industrial processes. However, a significant challenge persists regarding the long-term stability of Micro-Electro-Mechanical Systems (MEMS) sensors, which are prone to drift due to environmental fluctuations, mechanical aging, and thermal hysteresis. This paper presents a comprehensive methodology for the development of self-calibrating smart sensors utilizing Kalman filtering and sensor fusion techniques.
By integrating multiple sensing modalities, specifically inertial and magnetic measurements, within a recursive estimation framework, we propose a robust system capable of estimating and compensating for sensor bias in real-time. The approach eliminates the need for frequent manual recalibration, thereby reducing maintenance costs and operational downtime. We describe the theoretical underpinnings of the Extended Kalman Filter (EKF) applied to non-linear sensor models and detail the hardware implementation on a standard embedded microcontroller.
Experimental validation demonstrates that the proposed fusion algorithm maintains high measurement fidelity under varying thermal conditions and mechanical vibration, significantly outperforming single-sensor solutions and static calibration methods. The results suggest that autonomous self-calibration is a viable pathway for enhancing the reliability of large-scale industrial automation systems.
Open the resolved locator · 10.71465/csb196
Metadata licence: OpenAlex metadata (CC0)