In order to improve the accuracy of an infrared thermometer, the main uncertainty sources of the system are analyzed and a compensation function is established on the basis of these corrections. The verification experiments are carried out by using a self-developed infrared thermometer and a blackbody. The experimental results indicate that the compensation function can reduce the infrared thermometer expanded uncertainty from ±3.6 °C to ±1.9 °C in the temperature range of −40 °C to 60 °C. This method can effectively improve the temperature measurement accuracy of an ambient temperature infrared thermometer in its measurement range.

The data processing of multi-wavelength pyrometry (MWP) is faced with the problem of solving N equations and N+1 unknown underdetermined equations. The traditional iterative optimization methods are difficult to meet the actual measurement requirements in terms of accuracy and efficiency. With the development of artificial intelligence technology in the field of data processing, it is expected to solve this problem. A generalized inverse matrix (GIM) is combined with a long short-term memory (LSTM) neural network algorithm for data processing of MWP is proposed, which emissivity influence is dispensed completely. Firstly, GIM is used for classification of the emissivity. Furthermore, inputting to the LSTM network not only ensures the accuracy of temperature measurement but also greatly improves the efficiency. The simulation results demonstrated that the accuracy of the GIM-LSTM algorithm was superior to that of the GIM-EPF and BP methods. After random noise was added, the relative error was still less than that for the GIM-EPF and BP methods, and the algorithm exhibited excellent anti-noise performance. Publicly available temperature data for the exhaust plume of a rocket engine were processed by the GIM-LSTM method, and the average relative error was less than the traditional method. Especially, in terms of inversion speed, the operational time of the GIM-LSTM algorithm was at the millisecond level, which is of great significance for the real-time monitoring of rocket exhaust plumes. The proposed GIM-LSTM data processing algorithm affords high accuracy and speed and is suitable for practical measurement of high-emissivity objects in real-time via MWP.

Neural networks are the most promising tool to solve the problem that an assumed emissivity model is needed in the field of multispectral radiometric temperature measurement. Existing neural network multispectral radiometric temperature measurement algorithms have been investigating the problems of network selection, network porting, and parameter optimization. The inversion accuracy and adaptability of the algorithms have been unsatisfactory. In view of the great success of deep learning in the field of image processing, this Letter proposes the idea of converting one-dimensional multispectral radiometric temperature data into two-dimensional image data for data processing to improve the accuracy and adaptability of multispectral radiometric temperature measurement by deep learning algorithms. Simulation and experimental validation are carried out. In the simulation, the error is less than 0.71% without noise and 1.80% with 5% random noise, which improves the accuracy by more than 1.55% and 2.66% compared with the classical BP (backpropagation) algorithm, and 0.94% and 0.96% compared with the GIM-LSTM (generalized inverse matrix–long short-term memory) algorithm. In the experiment, the error is less than 0.83%. This indicates that the method has high research value and is expected to lead multispectral radiometric temperature measurement technology to a new level.

A generalized inverse matrix-recurrent neural network (GIM-RNN) data processing algorithm for unknown emissivity was proposed to measure high-temperature by multiwavelength pyrometer (MWP). First, emissivity classification was realized quickly according to a solution from generalized inverse algorithm to underdetermined multiwavelength equation group. According to the relationship between the emissivity of 2 adjacent channels of the 6 channel thermometer used in this paper, 243 emissivity models (1 * 3 * 3 * 3 * 3 * 3) were designed for classification. Twelve of them were shown on the schematic diagram in the text. To make the figure clear and easy to observe, the prediction results of six common emissivity models were listed as the experimental results. Then, it was input into the corresponding RNN subnetwork to inverse temperature precisely. Simulation results showed that in the range of 1500 to 3000 K temperature, the relative error of the test set was within 1.0% for the network trained after classification by GIM, whereas the relative error of the test set was within 1.2% for the network trained without GIM classification. After 5.0% random noise was added to the inputting data, the relative error still was controlled within 1.5%, which reflected the good antinoise performance of the algorithm. Multispectral measurement data of rocket engine plumes is processed by the proposed algorithm in this manuscript. The inversion results are consistent with the theoretical results. It is indicated that the proposed algorithm has good adaptability to different materials. It is expected to become a general data processing algorithm for MWP.

This paper proposes a multispectral temperature measurement method integrating multiple information sources to address inaccuracies in target temperature measurements in multispectral thermometry when emissivity is unknown. This algorithm leverages convolutional neural networks for image recognition to convert one-dimensional voltage data into two-dimensional voltage spectral images. To enhance accuracy, it combines emissivity trend inversion with emissivity constraint algorithms. Additionally, a temperature-constraint function algorithm is incorporated to improve the computational speed. Through simulation experiments and comparative tests, the algorithm achieved a relative error below 0.08% and an absolute error below 2 K within a temperature range of 1000 to 4000 K, with an average runtime under 5 ms. The experimental results demonstrate that the method not only addresses efficiency issues in multispectral thermometry but also enhances temperature measurement accuracy, providing crucial technical support for industrial applications of multispectral thermometry.

The multispectral radiometric temperature measurement technique is affected by the unknown emissivity, and there is no multispectral radiometric temperature inversion algorithm applicable to any scene or target. To address the above problems, this paper converts the multispectral radiometric temperature inversion problem into an image recognition problem containing the temperature information to be measured, and proposes a graphical multispectral radiometric temperature adaptive inversion algorithm. In this paper, we use the difference between spectral channels to convert the one-dimensional radiation data into a two-dimensional radiation map; use the generalized inverse to obtain the spectral emissivity distribution features, fuse them with the two-dimensional radiation map, and use an improved deep learning network to achieve adaptive temperature inversion. It is experimentally verified that the algorithm proposed in this paper can achieve simultaneous inversion of temperature and emissivity for any scene or target with sufficient data set.