Deep Learning-Based Calibration of a Multi-Point Thin-Film Thermocouple Array for Temperature Field Measurement

Multi-point array thin-film thermocouples have strong potential for high-precision, wide-range temperature monitoring in applications such as aircraft engine thermal condition assessment and industrial process control. However, conventional single-point thin-film thermocouples cannot satisfy the distributed measurement requirements of large-area temperature fields, and the accuracy of multi-point arrays is often degraded by coupling effects among sensing nodes, which hinders their engineering deployment. In this work, a multi-point array thin-film thermocouple is fabricated via precision welding, and an insulating layer is deposited on the sensor surface using electrospray atomization to establish a multi-point temperature-sensing hardware system. To compensate for coupling-induced deviations, a deep learning-based calibration method is developed: measurements from the array and reference thermocouples are synchronously collected to build the dataset, outliers are removed using the interquartile range (IQR) method, and a three-hidden-layer multilayer perceptron (MLP) is trained for each node independently using the Adam optimizer (learning rate 0.001) with an 8:2 train-test split. Performance is quantified by MAE, MSE, and R², and the results show that the proposed approach markedly reduces measurement errors and improves the accuracy of the array thermocouples, demonstrating reliable performance and practical applicability for precise large-area temperature-field monitoring.