The paper reports an adaptive-network-based fuzzy inference system for the measurement of axial strain using long-period fiber grating sensors. The long-period fiber grating sensor supports optical resonances, which are sensitive to the change of axial strain. The axial strain can be quantified based on the wavelength shift and amplitude changes of the optical resonance. To improve the accuracy of axial strain quantification, this paper proposes the adaptive-network-based fuzzy inference system model. The adaptive-network-based fuzzy inference system model is trained using the strain data measured with long-period fiber grating sensors. The parameters of the membership functions used in the adaptive-network-based fuzzy inference system are set adaptively. In the adaptive-network-based fuzzy inference system–based method, the maximum relative error was found to be 1.5%, which is about one-ninth of that when the data fitting method was used. The R-squared statistics using the adaptive-network-based fuzzy inference system model is 0.9872, while that using the linear fitting algorithm is 0.8815. Compared with the conventional data fitting methods, the proposed approach is highly adaptive and versatile with the capability of improving the accuracy of strain quantification.

In this study, a new square-based fiber Bragg grating (FBG) sensor network model is proposed to address possible link failures in FBG sensor networks and improve their reliability. Graph theory and optical switching are simultaneously applied to these sensor networks to improve their self-healing ability; the FBG sensor network is regarded as a directed graph. Three commonly used self-short-circuit algorithms are compared in terms of the self-healing capabilities that they provide to the optical fiber sensor network. Among these, the shortest-path faster algorithm achieved a high, nearly 90% repair accuracy and had an average repair time of 0.103 s, the shortest in this study. The newly designed FBG self-healing network can be reorganized and repaired when local damage occurs, thereby improving its reliability.

A single long period grating is used for simultaneous measurement of temperature and strain in this article. To decrease the effect of cross-sensitivity effectively, a support vector regression (SVR) method is proposed due to its characteristics to approximate nonlinear function in the whole region. By detecting the shifts of LPG’s different loss peaks’ resonant wavelength, the temperature and strain were obtained by way of regression prediction where proper parameters were chosen. Some comparisons between the SVR and a standard matrix inversion method were made; the root-mean-square errors of two methods are 0.1746°C, 3.82 με and 2.981°C, 28.61 με, respectively. The experimental results show that SVR has advantages such as excellent learning performance of small samples, good generalization ability, small errors, high calculation accuracy, etc.

This study proposes a long‐period fibre grating (LPFG) curvature estimation method based on random forest regression (RFR) to address the shortcomings of the existing curvature evaluation method, namely, polynomial fitting; these shortcomings cause difficulty in achieving adequate model regularity and application universality. The resonant wavelength and resonant peak amplitude of the LPFG are used as input variables in this method to develop an RFR model for curvature estimation, allowing for accurate curvature prediction of the sample. The results show that the RFR‐based LPFG curvature prediction model can better characterise the input–output regression relationship than back‐propagation neural networks. The average R ² value of the RFR model is 0.9826, and the actual measured curvature value is highly correlated with the model predicted curvature value. Compared to that exhibited by back‐propagation neural networks, the RFR model exhibits higher accuracy for curvature estimation, with average values of 0.1314 and 0.1173 for root mean square and mean absolute errors, respectively. This method can provide a more comprehensive theoretical basis for the application of robot learning in the curvature measurement of LPFG and has practical value.