Page 34 - 陽明交大電機學院院刊 2025.02

重要論文

第三季重要論文 (2024 年 7-9 月) 獲選刊登本校研發處首頁

IEEE Transactions on Industrial Informatics

A New FPGA-Implemented Neural Network for
Compensating Degradation of AMOLED Displays in Real
Time for Long Operation With Temperature Considered

2024/09,

電控工程研究所 趙昌博 講座教授（通訊作者）

A new neural network (NN) model is algorithms are implemented into hardware via
established for compensating effectively in the technology of field programmable gate
array (FPGA), with the platform of Xilinx
real time the luminance degradation of
Vivado 2020.1 for realizing the associated
organic light emitting diodes (OLEDs) in a
display operated for an extensive period. The codes in Verilog. Based on experimental data,
compensation is achieved by three stages of the compensation logics in the FPGA board
led to the averaged displaying accuracies of
models. First, a model was orchestrated to

estimate well the temperature distribution of 97.1%, 93.9%, and 95.1% for red, green, and
an OLED display. Second, a new, incremental blue OLEDs, respectively, with respect to
target luminances over a long period of 1000
NN was established based on collected data of
degraded OLED luminance with ambient h, showing the best performance over all the

temperature recorded. Third, another other works reported in the past. The
presented excellent performance attributes are
algorithm in logic based on interpolation is
mainly due to the consideration of
designed to compensate effectively the

degraded OLED luminance in real-time temperature as one of the inputs to the built
operation of the OLED displays in the shortest degradation NN model and the incremental
nature of the model.
time possible. All the above-mentioned 3

33