A strain sensor based on cascaded Sagnac loops with two polarization-maintaining photonic crystal fibers (PMPCFs) has been experimentally demonstrated. Air holes distributed on the cross section of PMPCF go through the whole fiber, which makes the special fiber more sensitive to ambient force compared with conventional optical fiber. The lengths of the two PMPCFs are close, but not the same, to form envelopes on the total output spectrum and then obtain high resolution to the detected parameter by the Vernier effect. The influences of the difference in length of the two PMPCFS on spectral envelopes are discussed. As the length of the PMPCF in reference loop increases, free spectrum range of the cascaded Sagnac loops (or envelope period) and magnification decrease. The sensitivities of this strain sensor are calculated by tracking upper and lower envelopes. Results reveal that its average sensitivity is up to 45.15 pm/ $\mu \varepsilon $ and the corresponding resolution is $0.44~\mu \varepsilon $ as strain varies from 0 to $2000~\mu \varepsilon $ . Compared with a single Sagnac loop, the sensitivity magnification is about 28.94. The sensing characteristics of a conventional polarization-maintaining fiber (PMF) are studied to compare with the PMPCF. Moreover, reversibility has also been proved to possess low error rate. In short, the fiber strain sensor possesses high sensitivity and great reversibility.
10 March 2023 in Ironmaking & Steelmaking: Processes, Products and Applications
Owing to the uncertainty operation in the sintering process, it is easy to produce uncertain prediction errors in the single drum index prediction model, which makes the prediction results lack certain reliability. Accurate and reliable prediction of the drum index can help improve the drum index. In this paper, a prediction interval estimation method of drum index based on a light gradient boosting machine (LightGBM) and kernel density estimation (KDE) is proposed. LightGBM can obtain accurate points prediction of drum index, and then use the KDE method to obtain the estimated prediction interval of drum index. The comparison results of different methods show that LightGBM has high prediction performance, and KDE can well quantify the prediction error of drum index, which verifies the effectiveness of the prediction interval estimation method combined with LightGBM and KDE, and provides more reliable decision-making information for the optimisation of sintering process parameters.
The design and optimization of a sinter mixture moisture controlling system usually require complex process mechanisms and time-consuming field experimental simulations. Based on BP neural networks, a new KPCA-GA optimization method is proposed to predict the mixture moisture content sequential values with time more accurately so as to derive the optimal water addition to meet industrial requirements. Firstly, the normalized input variables affecting the output were dimensionalized using kernel principal component analysis (KPCA), and the contribution rates of the factors affecting the water content were analyzed. Then, a BP neural network model was established. In order to get rid of the randomness of the initial threshold and weights on the prediction accuracy of the model, a genetic algorithm is proposed to preferentially find the optimal initial threshold and weights for the model. Then, statistical indicators, such as the root mean square error, were used to evaluate the fit and prediction accuracy of the training and test data sets, respectively. The available experimental data show that the KPCA-GA model has high fitting and prediction accuracy, and the method has significant advantages over traditional neural network modeling methods when dealing with data sets with complex nonlinear characteristics, such as those from the sintering process.