To solve the problem of the measured value of pressure scanners drifting nonlinearly with temperature change when measuring pressure, resulting in low accuracy, this paper proposes and develops a new calibration system based on neural networks for pressure scanners. Specifically, we start by calibrating the pressure scanner production process, then design the sealing device applicable to the working environment of pressure scanner, and finally install the calibration system of pressure scanner for calibration experiments, so that accurate measurement results can be obtained. In addition, at the algorithmic level, this paper proposes a whale optimization algorithm based back propagation (BP) neural network method instead of the traditional least squares method to complete the temperature compensation. Both the off-line compensation results and the compensated on-line experimental results show the high measurement accuracy of this temperature compensation method. The full-scale error (FS) is 0.07%, the coefficient of determination (R2) =99.27%, with similar results for all channels of the pressure sensor in the temperature environment -40°C to 60°C and absolute pressures ranging from 0 to 1.1Mpa. The result is not only a significant reduction in full-scale error of 0.25%, R2 =91.32% based on conventional algorithm compensation, but also applies to the pressure scanner with wide temperature region, wide range and high accuracy temperature compensation, which is important for its future research of low-cost overall calibration and high accuracy algorithms.