No abstract

No abstract

Brillouin optical time domain analyzer (BOTDA) assisted by optimized support vector machine (SVM) algorithm for accurate temperature extraction is presented and experimentally demonstrated. Three typical intelligent optimization algorithms, particle swarm optimization algorithm, genetic algorithm and firefly algorithm are explored to optimize the SVM parameters. The performances of optimized SVM algorithms for temperature extraction are investigated in both simulation and experiment under different conditions for Brillouin gain spectrum collection, resulting in the significant enhancement of sensing accuracy. In particular, the extraction accuracy (i.e., smaller root mean square error value) of temperature information is improved about 4°C compared with the conventional SVM when the signal-to-noise ratio (SNR) as low as 2.5 dB and 40-ns pump pulse width are adopted in the experiment. In addition to the enhanced accuracy with good robustness, the optimized algorithms have faster processing speed than the curve fitting method, over 20-times improvement. That makes the optimized algorithms become a very promising candidate for high performance BOTDA sensors in the future.

The initial state of a nonlinear optical fiber system plays a vital role in the ultrafast pulse evolution dynamic. In this work, a data-driven compressed convolutional neural network, named inverse network, is proposed to predict initial pulse distribution through a series of discrete power profiles at different propagation distances. The inverse network is trained and tested based on two typical nonlinear dynamics: (1) the pulse evolution in a fiber optical parametric amplifier system and (2) soliton pair evolution in high-nonlinear fibers. Great prediction accuracy is reached when the epoch grows to 5000 in both cases, with the normalized root mean square errors below 0.01 on the entire testing set. Meanwhile, the lightweight network is highly effective. In this work, it takes approximately 30 seconds for 5,000 epochs training with a dataset size of 900. The inverse network is further tested and analyzed on the dataset with different signal-to-noise ratios and input sizes. The results show fair stability at the deviation on the testing set. The proposed inverse network demonstrates a promising approach to optimizing the initial pulse of fiber optics systems.

No abstract